Paper  bibtex   

@incollection{delmonte_exploring_2011,
	Address = {Rijeka},
	Author = {Delmonte, Rodolfo},
	Booktitle = {Speech and language technology},
	Editor = {Ipsic, Ivo},
	File = {Attachment:files/2955/Delmonte - 2011 - Exploring speech technologies for language learning.pdf:application/pdf},
	Keywords = {applications, L2, L2 teaching, pronunciation teaching, speech technology},
	Note = {bibtex: delmonte\_exploring\_2011},
	Pages = {71--104},
	Publisher = {In Tech},
	Title = {Exploring speech technologies for language learning},
	Url = {http://www.intechopen.com/books/speech-and-language-technologies/exploring-speech-technologies-for-language-learning},
	Year = {2011},
	Bdsk-Url-1 = {http://www.intechopen.com/books/speech-and-language-technologies/exploring-speech-technologies-for-language-learning}}

Paper  bibtex   

@book{verma_google_2011,
	Author = {Verma, Awaneesh},
	File = {Attachment:files/11469/Verma - 2011 - Google Translate blog.pdf:application/pdf},
	Keywords = {applications, Spanish, speech technology, spoken language translation},
	Note = {bibtex: verma\_google\_2011},
	Title = {Google {Translate} blog},
	Url = {http://googletranslate.blogspot.com/2011/01/new-look-for-google-translate-for.html},
	Year = {2011},
	Bdsk-Url-1 = {http://googletranslate.blogspot.com/2011/01/new-look-for-google-translate-for.html}}

Paper  abstract   bibtex   

@article{espejo_sistema_2010,
	Abstract = {Mayordomo es un sistema de di{\'a}logo multimodal que permite la interacci{\'o}n con un entorno de Inteligencia Ambiental para una vivienda. Este sistema permite la manipulaci{\'o}n de los electrodom{\'e}sticos instalados en la vivienda de manera oral, escrita y a trav{\'e}s de una interfaz gr{\'a}fica. Tambi{\'e}n incluye una serie de funcionalidades adicionales, incluyendo, acceso identificado de usuarios, control parental e historial de acciones realizadas por los usuarios.},
	Author = {Espejo, Gonzalo and {\'A}balos, Nieves and L{\'o}pez-C{\'o}zar, Ram{\'o}n and Callejas, Zoraida and Griol, David},
	Journal = {Procesamiento del Lenguaje Natural},
	Keywords = {applications, dialogue systems, speech technology},
	Note = {bibtex: espejo\_sistema\_2010},
	Pages = {309--310},
	Title = {Sistema {Mayordomo}: {Uso} de un entorno de inteligencia ambiental a trav{\'e}s de un sistema de di{\'a}logo multimodal},
	Url = {http://www.sepln.org/ojs/ojs-2.2/index.php/pln/article/view/816/670},
	Volume = {45},
	Year = {2010},
	Bdsk-Url-1 = {http://www.sepln.org/ojs/ojs-2.2/index.php/pln/article/view/816/670}}

@phdthesis{san_segundo_estudio_2009,
	Address = {Madrid},
	Author = {San Segundo, Eugenia},
	Keywords = {acoustic phonetics, forensic, forensic phonetics, phonetics, speaker recognition, speech technology},
	Note = {bibtex: san\_segundo\_estudio\_2009},
	School = {Consejo Superior de Investigaciones Cient{\'\i}ficas - Universidad Internacional Men{\'e}ndez Pelayo},
	Title = {Estudio de los par{\'a}metros ac{\'u}sticos referidos a los resonadores del tracto vocal (par{\'a}metros form{\'a}nticos) y su utilidad para la identificaci{\'o}n de hablantes},
	Year = {2009}}

Paper  abstract   bibtex   

@phdthesis{pruthi_analysis_2007,
	Abstract = {The aim of this work is to clearly understand the salient features of nasalization and the sources of acoustic variability in nasalized vowels, and to suggest Acoustic Parameters (APs) for the automatic detection of vowel nasalization based on this knowledge. Possible applications in automatic speech recognition, speech enhancement, speaker recognition and clinical assessment of nasal speech quality have made the detection of vowel nasalization an important problem to study. Although several researchers in the past have found a number of acoustical and perceptual correlates of nasality, automatically extractable APs that work well in a speaker-independent manner are yet to be found. In this study, vocal tract area functions for one American English speaker, recorded using Magnetic Resonance Imaging, were used to simulate and analyze the acoustics of vowel nasalization, and to understand the variability due to velar coupling area, asymmetry of nasal passages, and the paranasal sinuses. Based on this understanding and an extensive survey of past literature, several automatically extractable APs were proposed to distinguish between oral and nasalized vowels. Nine APs with the best discrimination capability were selected from this set through Analysis of Variance. The performance of these APs was tested on several databases with different sampling rates, recording conditions and languages. Accuracies of 96.28\%, 77.90\% and 69.58\% were obtained by using these APs on StoryDB, TIMIT and WS96/97 databases, respectively, in a Support Vector Machine classifier framework. To my knowledge, these results are the best anyone has achieved on this task. These APs were also tested in a cross-language task to distinguish between oral and nasalized vowels in Hindi. An overall accuracy of 63.72\% was obtained on this task. Further, the accuracy for phonemically nasalized vowels, 73.40\%, was found to be much higher than the accuracy of 53.48\% for coarticulatorily nasalized vowels. This result suggests not only that the same APs can be used to capture both phonemic and coarticulatory nasalization, but also that the duration of nasalization is much longer when vowels are phonemically nasalized. This language and category independence is very encouraging since it shows that these APs are really capturing relevant information.},
	Address = {Ann Arbor, MI},
	Author = {Pruthi, Tarun},
	Keywords = {acoustic phonetics, consonants, nasals, phonetic knowledge, phonetics, segmental, speech recognition, speech technology, vowels},
	Note = {bibtex: pruthi\_analysis\_2007},
	School = {University of Maryland, College Park},
	Title = {Analysis, vocal-tract modeling and automatic detection of vowel nasalization},
	Url = {http://hdl.handle.net/1903/4273},
	Year = {2007},
	Bdsk-Url-1 = {http://hdl.handle.net/1903/4273}}

@inproceedings{gonzalez_gonzalez_seaf_2007,
	Address = {Santiago de Compostela},
	Editor = {Gonz{\'a}lez Gonz{\'a}lez, Manuel and Fern{\'a}ndez Rei, Elisa and Gonz{\'a}lez Rei, Bego{\~n}a},
	Isbn = {978-84-453-4450-7},
	Keywords = {forensic, forensic phonetics, proceedings, speaker recognition, speech technology},
	Note = {bibtex: gonzalez\_gonzalez\_seaf\_2007},
	Publisher = {Xunta de Galicia},
	Title = {{SEAF} 2005. {Actas} do {III} {Congreso} da {Sociedade} {Espa{\~n}ola} de {Ac{\'u}stica} {Forense}},
	Year = {2007}}

Paper  bibtex   

@inproceedings{llisterri_les_2007,
	Address = {Servei de Tecnologia Ling{\"u}{\'\i}stica, Facultat de Filologia, Universitat de Barcelona, 10 de enero de 2007},
	Author = {Llisterri, Joaquim},
	Booktitle = {Jornada "{Aplicacions} del processament del llenguatge natural"},
	Keywords = {CV, CV congressos, CV congressos confer{\`e}ncia, general, speech technology},
	Note = {bibtex: llisterri\_les\_2007},
	Title = {Les tecnologies de la parla},
	Url = {http://liceu.uab.cat/$\sim$joaquim/speech_technology/UB_07/UB_07.html},
	Year = {2007},
	Bdsk-Url-1 = {http://liceu.uab.cat/$%5Csim$joaquim/speech_technology/UB_07/UB_07.html}}

@incollection{black_multilingual_2006,
	Address = {Burlington, MA},
	Author = {Black, Alan W},
	Booktitle = {Multilingual speech processing},
	Editor = {Schultz, Tanja and Kirchhoff, Katrin},
	File = {Attachment:files/1218/Black - 2006 - Multilingual speech synthesis.pdf:application/pdf},
	Keywords = {general, speech synthesis, speech technology},
	Note = {bibtex: black\_multilingual\_2006},
	Pages = {207--231},
	Publisher = {Elsevier Academic Press},
	Title = {Multilingual speech synthesis},
	Year = {2006}}

Paper  bibtex   

@inproceedings{llisterri_perfil_2006,
	Address = {Universidad Aut{\'o}noma de Madrid., Universitat Aut{\`o}noma de Barcelona, Ambassade de France en Espagne. Madrid, 30-31 de marzo de 2006},
	Author = {Llisterri, Joaquim},
	Booktitle = {Jornadas internacionales "{Nuevas} profesiones en el {\'a}mbito de la comunicaci{\'o}n pluriling{\"u}e"},
	Keywords = {CV, CV congressos, CV congressos taula rodona, CV xarxes liceu, language technology, speech technology},
	Note = {bibtex: llisterri\_perfil\_2006},
	Title = {El perfil del linguista inform{\'a}tico},
	Url = {http://liceu.uab.cat/$\sim$joaquim/language_technology/UAM_06/Perfil_Linguista_Informatico_UAM_06.pdf},
	Year = {2006},
	Bdsk-Url-1 = {http://liceu.uab.cat/$%5Csim$joaquim/language_technology/UAM_06/Perfil_Linguista_Informatico_UAM_06.pdf}}

Paper  doi  abstract   bibtex   

@article{toda_evaluation_2006,
	Abstract = {In this paper, we evaluate various cost functions for selecting a segment sequence in terms of the correspondence between the cost and perceptual scores to the naturalness of synthetic speech. The results demonstrate that the conventional average cost, which shows the degradation of naturalness over the entire synthetic utterance, has better correspondence to the perceptual scores than the maximum cost, which shows the worst local degradation of naturalness. Furthermore, it is shown that root mean square (RMS) cost, which takes into account both the average cost and the maximum cost, has the best correspondence. We also show that the naturalness of synthetic speech can be improved by using the RMS cost for segment selection. Then, we investigate the effects of applying the RMS cost to segment selection in comparison to those of applying the average cost. Experimental results show that in segment selection based on the RMS cost, a larger number of concatenations causing slight local degradation are performed so that concatenations causing greater local degradation are avoided.},
	Author = {Toda, Tomoki and Kawai, Hisashi and Tsuzaki, Minoru and Shikano, Kiyohiro},
	Doi = {10.1016/j.specom.2005.05.011},
	Issn = {01676393},
	Journal = {Speech Communication},
	Keywords = {speech synthesis, speech technology, text-to-speech, unit selection},
	Month = jan,
	Note = {bibtex: toda\_evaluation\_2006},
	Number = {1},
	Pages = {45--56},
	Title = {An evaluation of cost functions sensitively capturing local degradation of naturalness for segment selection in concatenative speech synthesis},
	Url = {http://linkinghub.elsevier.com/retrieve/pii/S0167639305001366},
	Volume = {48},
	Year = {2006},
	Bdsk-Url-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0167639305001366},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.specom.2005.05.011}}

Paper  bibtex   

@book{nileinne_windows_2006,
	Author = {{NilEinne}},
	Keywords = {speech recognition, speech recognition system, speech technology},
	Note = {bibtex: nileinne\_windows\_2006},
	Title = {Windows {Vista} speech recognition - the whole story},
	Url = {http://www.youtube.com/watch?v=kX8oYoYy2Gc},
	Year = {2006},
	Bdsk-Url-1 = {http://www.youtube.com/watch?v=kX8oYoYy2Gc}}

Paper  doi  abstract   bibtex   

@article{rodriguez_fuentes_spontaneous_2006,
	Abstract = {Previous works in English have revealed that disfluencies follow regular patterns and that incorporating them into the language model of a speech recognizer leads to lower perplexities and sometimes to a better performance. Although work on disfluency modeling has been applied outside the English community (e.g., in Japanese), as far as we know there is no specific work dealing with disfluencies in Spanish. In this paper, we follow a data driven approach in exploring the potential benefit of modeling disfluencies in a speech recognizer in Spanish. Two databases of human-computer and human-human dialogs are considered, which allow the absolute and relative frequencies of disfluencies in the two situations to be compared. The rate of disfluencies in human-human dialogs is found to be very close to that found for similar databases in English. Due to setup factors, the rate of disfluencies found in human-computer dialogs was remarkably higher than that reported for similar databases in English. In any case, from the point of view of speech recognition, the high frequencies of disfluencies and the distinct features of the acoustic events related to them support the need for explicit acoustic models. The regularities observed in the distribution of filled pauses and speech repairs reveal that including them in the language model of the speech recognizer may be also helpful. The extent to which the number of events depends on utterance length and on the speaker is also explored. Statistics are shown that follow previous studies for English, and a sizeable space is devoted to comparing our results with them. Finally, various possible cues for the automatic detection of speech repairs--a key issue from the point of view of speech understanding--are explored: silent pauses, filled pauses, lengthenings, cut off words and discourse markers. As previously observed for English, none of them was found to be reliable by itself. More information, especially at the acoustic-prosodic level, is no doubt needed to reliably detect speech repairs.},
	Author = {Rodr{\'i}guez Fuentes, Luis Javier and Torres, Mar{\'i}a In{\'e}s},
	Date-Modified = {2016-09-24 18:56:14 +0000},
	Doi = {10.1177/00238309060490030201},
	Issn = {0023-8309},
	Journal = {Language and Speech},
	Keywords = {corpus, dialogue systems, disfluencies, ESTIVOZ, language resources, phonetics, Spanish, speaking styles, speech corpus, speech technology, spontaneous speech},
	Number = {3},
	Pages = {333-366},
	Title = {Spontaneous speech events in two speech databases of human-computer and human-human dialogs in Spanish},
	Url = {http://las.sagepub.com/cgi/content/abstract/49/3/333 http://las.sagepub.com/cgi/doi/10.1177/00238309060490030201},
	Volume = {49},
	Year = {2006},
	Bdsk-Url-1 = {http://las.sagepub.com/cgi/content/abstract/49/3/333%20http://las.sagepub.com/cgi/doi/10.1177/00238309060490030201},
	Bdsk-Url-2 = {http://dx.doi.org/10.1177/00238309060490030201}}

@incollection{schultz_bibliography_2006,
	Address = {Burlington, MA},
	Author = {Schultz, Tanja and Kirchhoff, Katrin},
	Booktitle = {Multilingual speech processing},
	Editor = {Schultz, Tanja and Kirchhoff, Katrin},
	File = {Attachment:files/10306/Schultz, Kirchhoff - 2006 - Bibliography.pdf:application/pdf},
	Keywords = {multilingualism, per esborrar, speech technology},
	Note = {bibtex: schultz\_bibliography\_2006},
	Pages = {449--490},
	Publisher = {Elsevier Academic Press},
	Title = {Bibliography},
	Year = {2006}}

@incollection{barry_integration_2005,
	Address = {Dordrecht},
	Editor = {Barry, William J and van Dommelen, Wim A},
	Isbn = {978-1-4020-2635-5},
	Keywords = {general, phonetic knowledge, speech technology},
	Note = {bibtex: barry\_integration\_2005},
	Publisher = {Springer},
	Title = {The integration of phonetic knowledge in speech technology},
	Year = {2005}}

Paper  abstract   bibtex   

@article{campbell_developments_2005,
	Abstract = {This paper describes the special demands of conversational speech in the context of corpus-based speech synthesis. The author proposed the CHATR system of prosody-based unit-selection for concatenative waveform synthesis seven years ago, and now extends this work to incorporate the results of an analysis of five-years of recordings of spontaneous conversational speeech in a wide range of actual daily-life situations. The paper proposes that the expresion of affect (often translated as `kansei' in Japanese) is the main factor differentiating laboratory speech from realworld conversational speech, and presents a framework for the specification of affect through differences in speaking style and voice quality. Having an enormous corpus of speech samples available for concatenation allows the selection of complete phrase-sized utterance segments, and changes the focus of unit selection from segmental or phonetic continuity to one of prosodic and discoursal appropriateness instead. Samples of the resulting large-corpus-based synthesis can be heard at http://feast.his.atr.jp/AESOP.},
	Author = {Campbell, Nick},
	File = {Attachment:files/1849/Campbell - 2005 - Developments in corpus-based speech synthesis Approaching natural conversational speech.pdf:application/pdf},
	Journal = {IEICE Transactions on Information and Systems},
	Keywords = {speaking styles, speech synthesis, speech technology},
	Note = {bibtex: campbell\_developments\_2005},
	Number = {3},
	Pages = {376--383},
	Title = {Developments in corpus-based speech synthesis: {Approaching} natural conversational speech},
	Url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.8099&rep=rep1&type=pdf},
	Volume = {E88-D},
	Year = {2005},
	Bdsk-Url-1 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.8099&rep=rep1&type=pdf}}

Paper  bibtex   

@incollection{olaszy_phonetics_2005,
	Author = {Ol{\'a}szy, G{\'a}bor},
	Booktitle = {Forum {Acousticum} 2005},
	Keywords = {general, phonetic knowledge, speech technology},
	Note = {bibtex: olaszy\_phonetics\_2005},
	Pages = {2663--2667},
	Publisher = {Budapest, Hungary. 29 August - 2 September, 2005},
	Title = {Phonetics and speech technology},
	Url = {http://intellagence.eu.com/acoustics2008/acoustics2008/cd1/data/fa2005-budapest/paper/797-0.pdf},
	Year = {2005},
	Bdsk-Url-1 = {http://intellagence.eu.com/acoustics2008/acoustics2008/cd1/data/fa2005-budapest/paper/797-0.pdf}}

@article{drioli_emotions_2004,
	Author = {Drioli, Carlo and Tisato, Graziano and Cosi, Piero and Tesser, Fabio},
	Journal = {Quaderni della Sezione di Fonetica e Dialettologia dell'ISTC},
	Keywords = {emotions, phonation, phonetics, prosody, speaking styles, speech production, speech synthesis, speech technology, voice quality},
	Note = {bibtex: drioli\_emotions\_2004},
	Pages = {149--154},
	Title = {Emotions and voice quality: {Experiments} with sinusoidal modelling},
	Volume = {6},
	Year = {2004}}

Paper  abstract   bibtex   

@article{rose_strength_2003,
	Abstract = {A forensic-phonetic speaker identification experiment is described which tests to what extent same-speaker pairs from a 60 speaker Japanese data base can be discriminated from different-speaker pairs using a Bayesian likelihood ratio (LR) as discriminant function. Non-contemporaneous telephone recordings are used, with comparison based on mean values from three segments only: a nasal, a voiceless fricative, and a vowel. It is shown that discrimination using the LR-based distance is better than with a conventional distance, and that the cepstrum outperforms the formants. A LR for the test of 50 is obtained for formant-based discrimination, compared to c. 900 for the cepstrum, and the tests are thus shown to be capable of yielding a probative strength of support for the prosecution hypothesis that is conventionally quantified as `moderate' for formants but `moderately strong' for the cepstrum. Comparisons are made with results from similar experiments},
	Author = {Rose, Philip and Osanai, Takashi and Kinoshita, Yuko},
	Issn = {17488893},
	Journal = {International Journal of Speech, Language and the Law},
	Keywords = {forensic, forensic phonetics, speaker recognition, speech technology},
	Note = {bibtex: rose\_strength\_2003},
	Number = {2},
	Pages = {179--202},
	Title = {Strength of forensic speaker identification evidence: multispeaker formant- and cepstrum-based segmental discrimination with a {Bayesian} likelihood ratio as threshold},
	Url = {http://www.equinoxjournals.com/IJSLL/article/view/1992},
	Volume = {10},
	Year = {2003},
	Bdsk-Url-1 = {http://www.equinoxjournals.com/IJSLL/article/view/1992}}

Paper  abstract   bibtex   

@article{marin_placing_2002,
	Author = {Marín, Rafael and Aguilar, Lourdes and Casacuberta, David},
	Date = {2002},
	Date-Modified = {2018-06-02 19:46:29 +0000},
	Journal = {Language Design. Journal of Theoretical and Experimental Linguistics},
	Keywords = {disfluencies, pause location, pauses, phonetics, prosody, silent pauses, Spanish, speech synthesis, speech technology, temporal factors, text-to-speech, lexical stress, stress group},
	Pages = {49--66},
	Title = {Placing pauses in read spoken Spanish: a model and an algorithm},
	Url = {http://elies.rediris.es/Language_Design/LD4/marin-aguilar-casacuberta.pdf},
	Volume = {4},
	Year = {2002},
	Abstract = {The purpose of this work is to describe the appearance and location of typographically unmarked pauses in any Spanish text to be read. An experiment is designed to derive pause location from natural speech: results show that Intonation Group length constraints guide the appearance of pauses, which are placed depending on syntactic information. Then, a rule-based algorithm is developed to automatically place pauses whose performance is tested by means of qualitative tests. The evaluation shows that the system adequately places pauses in read texts, since it predicts 81\% of orthographically unmarked pauses; when pauses associated to punctuation signs are included, the percentage of correct prediction increases to 92\%},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://elies.rediris.es/Language_Design/LD4/marin-aguilar-casacuberta.pdf}}

Paper  bibtex   

@incollection{huckvale_speech_2002,
	Author = {Huckvale, Mark},
	Booktitle = {{ICSLP} 2002 - {Interspeech} 2002. {Proceedings} of the 7th {International} {Conference} on {Spoken} {Language} {Processing}},
	File = {Attachment:files/5438/Huckvale - 2002 - Speech synthesis, speech simulation and speech science.pdf:application/pdf},
	Keywords = {phonetic knowledge, speech synthesis, speech technology},
	Note = {bibtex: huckvale\_speech\_2002},
	Pages = {1261--1264},
	Publisher = {Denver, Colorado, USA, September 16-20, 2002},
	Title = {Speech synthesis, speech simulation and speech science},
	Url = {http://www.phon.ucl.ac.uk/home/mark/papers/icslp02synth.pdf},
	Year = {2002},
	Bdsk-Url-1 = {http://www.phon.ucl.ac.uk/home/mark/papers/icslp02synth.pdf}}

Paper  bibtex   

@article{llisterri_habla_2001,
	Author = {Llisterri, Joaquim},
	Date = {2001},
	Date-Modified = {2017-11-19 18:43:50 +0000},
	Issn = {1579-2803},
	Journal = {La Musa. Pensamiento, Universidad y Red},
	Keywords = {general, speech technology},
	Pages = {39-44},
	Title = {El habla como medio de acceso a la Sociedad de la Información},
	Url = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_01_Habla_Acceso_Sociedad_Informacion.pdf},
	Volume = {1},
	Year = {2001},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_01_Habla_Acceso_Sociedad_Informacion.pdf}}

Paper  bibtex   

@inproceedings{_eurospeech_2001,
	Address = {Aalborg, Denmark. September 3-7, 2001},
	Keywords = {proceedings, speech technology},
	Note = {bibtex: \_eurospeech\_2001},
	Title = {Eurospeech 2001 {Scandinavia}. {Proceedings} of the 7th {European} {Conference} on {Speech} {Communication} and {Technology}, 2nd {Interspeech} {Event}},
	Url = {http://www.isca-speech.org/archive/eurospeech_2001/index.html},
	Year = {2001},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive/eurospeech_2001/index.html}}

@book{oshaughnessy_speech_2000,
	Abstract = {1.- Introduction; 2.- Review of mathematics for speech processing; 3.- Speech production and acoustic phonetics; 4.- Hearing; 5.- Speech perception; 6.- Speech analysis; 7.- Coding of speech signals; 8.- Speech enhancement; 9.- Speech synthesis; 10.- Automatic speech recognition; 11.- Speaker recognition; Appendix: Computer sites for help on speech communication; References.},
	Address = {New York},
	Author = {O'Shaughnessy, Douglas},
	Edition = {2nd},
	File = {Attachment:files/8559/O'Shaughnessy - 2000 - Speech communication. Human and machine.pdf:application/pdf},
	Keywords = {phonetics, speech recognition, speech synthesis, speech technology, textbook},
	Note = {bibtex: oshaughnessy\_speech\_2000},
	Publisher = {IEEE Press},
	Title = {Speech communication. {Human} and machine},
	Year = {2000}}

Paper  bibtex   

@book{dutoit_short_1999,
	Address = {Mons},
	Author = {Dutoit, Thierry},
	File = {Attachment:files/3263/Dutoit - 1999 - A short introduction to text-to-speech synthesis.pdf:application/pdf},
	Keywords = {speech synthesis, speech technology, text-to-speech},
	Note = {bibtex: dutoit\_short\_1999},
	Publisher = {TCTS Lab, Facult{\'e} Polytechnique de Mons},
	Title = {A short introduction to text-to-speech synthesis},
	Url = {http://tcts.fpms.ac.be/synthesis/introtts_old.html},
	Year = {1999},
	Bdsk-Url-1 = {http://tcts.fpms.ac.be/synthesis/introtts_old.html}}

@inproceedings{batusek_text_1999,
	Abstract = {Some algorithms for preprocessing of some more complicated parts of Czech texts are presented in the paper. Preprocessor uses some rules taking into account word context. Some other problems with transcription of such complicated parts of text are discussed as well: influence of the speech rate and prosodic phrases segmentation. All the presented algorithms are implemented in the TTS system Demosthenes ([5,6]).},
	Address = {Berlin},
	Author = {Bat{\r u}{\v s}ek, Robert and Dvo{\v r}{\'a}k, Jan},
	Booktitle = {{TDS} 1999. {Text}, {Speech} and {Dialogue}. {Second} {International} {Workshop}. {Plzen}, {Czech} {Republic}, {September} 13--17, 1999 {Proceedings}},
	Doi = {10.1007/3-540-48239-3_38},
	Editor = {Matousek, V{\'a}clav and Mautner, Pavel and Ocel{\'\i}kov{\'a}, Jana and Sojka, Petr},
	Keywords = {Czech, language technology, linguistic processing, natural language processing, speech synthesis, speech technology, text pre-processing, text-to-speech},
	Note = {bibtex: batusek\_text\_1999},
	Pages = {209--214},
	Publisher = {Springer},
	Title = {Text preprocessing for {Czech} speech synthesis},
	Year = {1999},
	Bdsk-Url-1 = {http://dx.doi.org/10.1007/3-540-48239-3_38}}

Paper  abstract   bibtex   

@inproceedings{kamm_evaluating_1999,
	Abstract = {Spoken language systems (SLSs) for accessing information sources or services through the telephone network and the Internet are currently being trialed and deployed for a variety of tasks. Evaluating the usability of different interface designs requires a method for comparing performance of different versions of the SLS. Recently, Walker et al (1997) proposed PARADISE (PARAdigm for DIalogue System Evaluation) as a general methodology for evaluating SLSs. The PARADISE framework models user satisfaction with an SLS as a linear combination of measures reflecting both task success and dialogue costs. As a test of this methodology, we applied PARADISE to dialogues collected with three SLSs. This paper describes the salient measures identified using PARADISE within and across the three SLSs, and discusses the generalizability of PARADISE performance models.},
	Address = {San Jos{\'e}, CA},
	Author = {Kamm, Candace and Walker, Marilyn A and Litman, Diane J},
	Booktitle = {{AVIOS} 1999. {Proceedings} of the annual meeting of the {American} {Voice} {Input}/{Output} {Society}},
	Keywords = {assessment, dialogue systems, speech technology},
	Note = {bibtex: kamm\_evaluating\_1999},
	Pages = {187--197},
	Title = {Evaluating spoken language systems},
	Url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.13.9747&rep=rep1&type=pdf},
	Year = {1999},
	Bdsk-Url-1 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.13.9747&rep=rep1&type=pdf}}

Paper  abstract   bibtex   

@inproceedings{carvalho_concatenative_1998,
	Abstract = {This paper describes our on-going work in the area of text-tospeech synthesis, specifically on concatenative techniques. Our preliminary work consisted in investigating the current trends in concatenative synthesis and the problems that could arise when we apply the existing state-of-the art solutions to the specific case of European Portuguese. Our ultimate goal is to develop a text-to-speech system that could be trained for any speaker's voice in a fully automatic way, i.e., we would like to develop a customized text-to-speech synthesizer for any voice reading a predetermined text. Our first steps in this direction involved such issues as automatic segmentation and alignment of recorded speech, optimized inventory design for concatenative synthesis, unit selection and optimal coupling of the selected units.},
	Author = {Carvalho, Pedro M and de Oliveira, Lu{\'\i}s Caldas and Trancoso, Isabel and Viana, Maria do C{\'e}u},
	Booktitle = {{SSW}3-1998. {Proceedings} of the {Third} {ESCA}/{COCOSDA} {Workshop} on {Speech} {Synthesis}},
	File = {Attachment:files/2027/Carvalho et al. - 1998 - Concatenative speech synthesis for European Portuguese.pdf:application/pdf},
	Keywords = {Portuguese, speech synthesis, speech technology, text-to-speech, unit selection},
	Note = {bibtex: carvalho\_concatenative\_1998},
	Pages = {159--164},
	Publisher = {Jenolan Caves House, Blue Mountains, Australia, November 26-29, 1998},
	Title = {Concatenative speech synthesis for {European} {Portuguese}},
	Url = {http://www.inesc-id.pt/pt/indicadores/Ficheiros/3261.pdf},
	Year = {1998},
	Bdsk-Url-1 = {http://www.inesc-id.pt/pt/indicadores/Ficheiros/3261.pdf}}

Paper  abstract   bibtex   

@inproceedings{neto_large_1998,
	Abstract = {Due to the enormous development of large vocabu- lary, speaker-independent continuous speech recogni- tion systems, which occur essentially for the US En- glish language, there is a large demand of this kind of systems for other languages. In this paper we present the work done in the development of a large vocabu- lary, speaker-independent continuous speech recogni- tion hybrid system for the European Portuguese lan- guage. This is a difficult task due to the basic de- velopment stage of this technology in the European Portuguese language. The development of a system of this kind for a new language depends on the avail- ability of the appropriate source components, mainly a speech corpus and large amounts of texts. This work became possible due to the development of a new database (BD-PUBLICO), a large vocabulary speech corpus for the European Portuguese language devel- oped by us over the last two years.},
	Address = {Sidney Convention Centre, Sidney, Australia, 30 November - 4 December, 1998},
	Author = {Neto, Jo{\~a}o Paulo and Martins, Ciro A and Almeida, Lu{\'\i}s B},
	Booktitle = {{ICSLP} 1998. {Proceedings} of the 5th {International} {Conference} on {Spoken} {Language} {Processing}},
	File = {Attachment:files/8407/Neto, Martins, Almeida - 1998 - A large vocabulary continuous speech recognition hybrid system for the Portuguese language.pdf:application/pdf},
	Keywords = {Portuguese, speech recognition, speech recognition system, speech technology},
	Note = {bibtex: neto\_large\_1998},
	Title = {A large vocabulary continuous speech recognition hybrid system for the {Portuguese} language},
	Url = {http://www.shlrc.mq.edu.au/proceedings/icslp98/PDF/AUTHOR/SL980562.PDF},
	Year = {1998},
	Bdsk-Url-1 = {http://www.shlrc.mq.edu.au/proceedings/icslp98/PDF/AUTHOR/SL980562.PDF}}

Paper  bibtex   

@inproceedings{bimbot_speaker_1997,
	Address = {Rhodes, Greece. 22-25 September, 1997},
	Author = {Bimbot, Fr{\'e}d{\'e}ric and Hutter, H P and Jaboulet, C{\'e}dric and Koolwaaij, Johan and Lindberg, Johan and Pierrot, Jean-Benoı̂t},
	Booktitle = {Eurospeech 1997. {Proceedings} of the 5th {European} {Conference} on {Speech} {Communication} and {Technology}},
	Keywords = {speaker recognition, speech technology},
	Note = {bibtex: bimbot\_speaker\_1997},
	Pages = {971--974},
	Title = {Speaker verification in the telephone network: {Research} activities in the {CAVE} project},
	Url = {http://infoscience.epfl.ch/record/82425/files/jaboulet97.pdf},
	Year = {1997},
	Bdsk-Url-1 = {http://infoscience.epfl.ch/record/82425/files/jaboulet97.pdf}}

@book{meloni_fondements_1996,
	Address = {Paris},
	Editor = {M{\'e}loni, H},
	Keywords = {compilation, speech technology, textbook},
	Note = {bibtex: meloni\_fondements\_1996},
	Publisher = {AUPELF - UREF},
	Title = {Fondements et perspectives en traitement automatique de la parole},
	Year = {1996}}

Paper  abstract   bibtex   

@inproceedings{fujisaki_analysis_1994,
	Abstract = {The aim of the present study is to obtain an analytic and quantitative description of the prosodic characteristics of spoken Spanish and to find out the relationship between the description and the underlying linguistic and paralinguistic information. This paper presents results of our preliminary effort to apply a method of analysis of F\$ contours that has been proposed and proved to be valid for Japanese and several other languages. Analysis of utterances of declarative sentences of Spanish indicates the basic validity of the method and provides useful findings on the prosodic characteristics of accent and intonation in Spanish.},
	Address = {Yokohama, Japan, September 18-22, 1994},
	Author = {Fujisaki, Hiroya and Ohno, Sumio and Nakamura, Kei-ichi and Guirao, Miguelina and Gurlekian, Jorge A},
	Booktitle = {{ICSLP} 1994. {Proceedings} of the 3rd {International} {Conference} on {Spoken} {Language} {Processing}},
	File = {Attachment:files/4130/Fujisaki et al. - 1994 - Analysis of accent and intonation in Spanish based on a quantitative model.pdf:application/pdf},
	Keywords = {acoustic phonetics, intonation, lexical stress, phonetic knowledge, phonetics, prosody, Spanish, speech synthesis, speech technology, text-to-speech},
	Note = {bibtex: fujisaki\_analysis\_1994},
	Pages = {355--358},
	Title = {Analysis of accent and intonation in {Spanish} based on a quantitative model},
	Url = {http://www.isca-speech.org/archive/icslp_1994/i94_0355.html},
	Volume = {1},
	Year = {1994},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive/icslp_1994/i94_0355.html}}

@incollection{abe_strategy_1994,
	Author = {Abe, M and Mizuno, H},
	Booktitle = {{SSW}2-1994. {Proceedings} of the {Second} {ESCA}/{IEEE} {Workshop} on {Speech} {Synthesis}},
	Keywords = {speaking styles, speech synthesis, speech technology},
	Note = {bibtex: abe\_strategy\_1994},
	Pages = {41--44},
	Publisher = {Mohonk Mountain House, New Paltz, NY, USA, September 12-15, 1994},
	Title = {A strategy for changing speaking styles in text-to-speech systems},
	Year = {1994}}

@inproceedings{violaro_panorama_1993,
	Address = {Lisboa},
	Author = {Violaro, F{\'a}bio},
	Booktitle = {{EPLP} 1993. {Actas} do 1o {Encontro} de {Processamento} da {L{\'\i}ngua} {Portuguesa} {Escrita} e {Falada}},
	Keywords = {per esborrar, Portuguese, speech technology},
	Note = {bibtex: violaro\_panorama\_1993},
	Pages = {183--193},
	Title = {Panorama de investiga{\c c}{\~o}es em processamento de fala no {Brasil}},
	Year = {1993}}

@inproceedings{zue_signals_1991,
	Address = {Aix-en-Provence, France. 19-24 August, 1991},
	Author = {Zue, Victor},
	Booktitle = {{ICPhS} 1991. {Actes} du 12{\`e}me {Congr{\`e}s} {International} de {Sciences} {Phon{\'e}tiques}},
	Keywords = {speech technology, spoken language understanding},
	Note = {bibtex: zue\_signals\_1991},
	Pages = {74--83},
	Title = {From signals to symbols to meaning: {On} machine understanding of spoken language},
	Volume = {1},
	Year = {1991}}

@incollection{carre_perspectivas_1991,
	Address = {Madrid},
	Author = {Carr{\'e}, Ren{\'e}},
	Booktitle = {Las industrias de la lengua},
	Editor = {Vidal Beneyto, J},
	Keywords = {general, speech technology},
	Note = {bibtex: carre\_perspectivas\_1991},
	Pages = {370--374},
	Publisher = {Fundaci{\'o}n S{\'a}nchez Ruip{\'e}rez - Pir{\'a}mide},
	Title = {Perspectivas de investigaciones en comunicaci{\'o}n hablada},
	Year = {1991}}

Paper  bibtex   

@article{llisterri_algunes_1990,
	Author = {Llisterri, Joaquim},
	Date = {1990},
	Date-Modified = {2017-05-28 22:20:18 +0000},
	Issn = {0213-6546},
	Journal = {L{\'i}mits. Revista d'assaig i d'informaci{\'o} sobre les ci{\`e}ncies del llenguatge},
	Keywords = {CV, CV publicacions, CV publicacions article, CV xarxes liceu, phonetic knowledge, speech technology},
	Language = {ca},
	Pages = {19-32},
	Title = {Algunes reflexions sobre el paper de la ling{\"u}{\'i}stica en la tecnologia de la veu},
	Url = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_90_Fonetica_TecnolHabla.pdf},
	Volume = {8},
	Year = {1990},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_90_Fonetica_TecnolHabla.pdf}}

@incollection{levinson_reconocimiento_1989,
	Address = {Barcelona},
	Author = {Levinson, Stephen E and Liberman, Mark Y},
	Booktitle = {Ac{\'u}stica musical},
	Editor = {Agull{\'o}, J},
	Keywords = {general, speech recognition, speech technology},
	Note = {bibtex: levinson\_reconocimiento\_1989},
	Pages = {106--121},
	Publisher = {Prensa Cient{\'\i}fica},
	Title = {Reconocimiento del habla por medio de ordenadores},
	Year = {1989}}

Paper  abstract   bibtex   

@incollection{mangold_assessment_1989,
	Abstract = {Public systems with speech input have been more and more introduced in the last few years. By these systems a new form of information collection and information dissemination will be provided for the general public. People are up to now well acquainted with public announcement systems, which do not have a special information input or where they have to give their input information via touch tone telephones. At least the speech output side is often rather common to the unexperienced user. People use many such announcement services, like entertainment, time announcement, weather forecast etc. In most cases of such systems there is no speech input. To introduce now the more advanced and more general speech input is unusual for most users and therefore they have their first problems how to speak and interact with such a speech driven system. They expect a speech recognizer which is perfectly working and often they suppose the recognizer would be able to understand continuous speech. For the near future we will have two sides of the problem, how to guarantee a minimum recognition capability necessary for establishing a certain service and on the other side how to prepare the occasional user for such a system.},
	Author = {Mangold, H},
	Booktitle = {Proceedings of the {ESCA} {Tutorial} and {Research} {Workshop} on {Speech} {Input} / {Output} {Assessment} and {Speech} {Databases}},
	Keywords = {assessment, speech recognition, speech technology},
	Note = {bibtex: mangold\_assessment\_1989},
	Pages = {37--58},
	Publisher = {Noordwijkerhout, The Netherlands. September 20-23, 1989},
	Title = {Assessment of speech recognizers in public information and ordering systems},
	Url = {http://www.isca-speech.org/archive_open/sioa_89/sia_1037.html},
	Year = {1989},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive_open/sioa_89/sia_1037.html}}

@incollection{johannsen_speech_1983,
	Abstract = {Various authors have pointed out that humans can become quite adept at deriving phonetic transcriptions from speech spectrograms (as good as 90\% accuracy at the phoneme level). In this paper, we describe an expert system which attempts to simulate this performance. The speech spectrogram expert (SPEX) is actually a society made up of three experts: a 2-dimensional vision expert, an acoustic-phonetic expert, and a phonetics expert. The visual reasoning expert finds important visual features of the spectrogram. The acoustic-phonetic expert reasons about how visual features relate to phonemes, and about how phonemes change visually in different contexts. The phonetics expert reasons about allowable phoneme sequences and transformations, and deduces an English spelling for phoneme strings. The speech spectrogram expert is highly interactive, allowing users to investigate hypotheses and edit rules.},
	Author = {Johannsen, J and MacAllister, J and Michalek, T and Ross, S},
	Booktitle = {{ICASSP} 1983. {Proceedings} of the {IEEE} {International} {Conference} on {Acoustics}, {Speech} and {Signal} {Processing}},
	Keywords = {acoustic phonetics, phonetics, speech technology},
	Note = {bibtex: johannsen\_speech\_1983},
	Pages = {746--749},
	Publisher = {Boston, Massachusetts, USA. April 14-16, 1983},
	Title = {A speech spectrogram expert},
	Year = {1983}}

@article{zue_computer_1982,
	Author = {Zue, Victor},
	Journal = {Trends and Perspectives in Signal Processing},
	Keywords = {speech synthesis, speech technology},
	Note = {bibtex: zue\_computer\_1982},
	Number = {4},
	Pages = {7--9},
	Title = {Computer voice response and speech synthesis},
	Volume = {2},
	Year = {1982}}

@article{levinson_speech_1981,
	Author = {Levinson, Stephen E and Liberman, Mark Y},
	Journal = {Scientific American},
	Keywords = {general, speech recognition, speech technology},
	Note = {bibtex: levinson\_speech\_1981},
	Number = {4},
	Pages = {64--76},
	Title = {Speech recognition by computer},
	Volume = {244},
	Year = {1981}}

@article{levinson_reconocimiento_1981,
	Author = {Levinson, Stephen E and Liberman, Mark Y},
	Journal = {Investigaci{\'o}n y Ciencia},
	Keywords = {general, speech recognition, speech technology},
	Note = {bibtex: levinson\_reconocimiento\_1981},
	Pages = {38--51},
	Title = {Reconocimiento del habla por medio de ordenadores},
	Volume = {57},
	Year = {1981}}

Paper  bibtex   

@article{fant_speech_1962-1,
	Author = {Fant, Gunnar and M{\'a}rtony, J},
	Journal = {STL-QPSR. Speech, Music and Hearing - Quarterly Progress and Status Report},
	Keywords = {formant synthesis, speech synthesis, speech technology},
	Note = {bibtex: fant\_speech\_1962-1},
	Number = {2},
	Pages = {18--19},
	Title = {Speech synthesis. {Instrumentation} for parametric synthesis ({OVE} {II})},
	Url = {http://www.speech.kth.se/prod/publications/files/qpsr/1962/1962_3_2_018-019.pdf},
	Volume = {3},
	Year = {1962},
	Bdsk-Url-1 = {http://www.speech.kth.se/prod/publications/files/qpsr/1962/1962_3_2_018-019.pdf}}

Paper  abstract   bibtex   

@article{griol_integracion_2010,
	Author = {Griol, David and Patricio, M Á and Molina, J M and Arroyo, Á and Callejas, Zoraida and López-Cózar, Ramón},
	Date = {2010},
	Date-Modified = {2016-09-24 18:56:05 +0000},
	Journal = {Procesamiento del Lenguaje Natural},
	Keywords = {applications, dialogue systems, speech technology},
	Pages = {107-114},
	Title = {Integración de los sistemas de diálogo para la interacción en redes sociales},
	Url = {http://www.sepln.org/revistaSEPLN/revista/44/articulos/revista4424.pdf},
	Volume = {44},
	Abstract = {Con el desarrollo de la denominada Web 2.0 y el gran inter ́es y extensi ́on que han alcanzado actualmente las redes sociales, se est ́an introduciendo r ́apidamente un gran nu ́mero de aplicaciones que originan a la vez nuevas formas de comunicaci ́on e interacci ́on entre los usuarios. Por otro lado, la investigaci ́on en el campo de los sistemas de di ́alogo posee en la actualidad un gran nu ́mero de retos relativos a la introducci ́on de nuevas modalidades tanto de entrada como de salida, as ́ı como aplicaciones y metodolog ́ıas que favorezcan la adaptaci ́on de estos sistemas a las caracter ́ısticas y preferencias espec ́ıficas de cada usuario. Las redes sociales, y m ́as concretamente los mundos virtuales, suponen de este modo un escenario perfecto para llevar a cabo estas lineas de investigaci ́on. En este art ́ıculo presentamos un estudio relativo a la integraci ́on de sistemas de di ́alogo en redes sociales, describiendo en nuestro trabajo la utilizaci ́on de un sistema de di ́alogo que proporciona informaci ́on acad ́emica para crear un avatar conversacional dentro del mundo virtual de Second Life.},
	Bdsk-Url-1 = {http://www.sepln.org/revistaSEPLN/revista/44/articulos/revista4424.pdf}}

Paper  bibtex   

@incollection{delmonte_exploring_2011,
	Address = {Rijeka},
	Author = {Delmonte, Rodolfo},
	Booktitle = {Speech and language technology},
	Date = {2011},
	Date-Modified = {2016-09-24 18:56:01 +0000},
	Editor = {Ipsic, Ivo},
	File = {Attachment:files/2955/Delmonte - 2011 - Exploring speech technologies for language learning.pdf:application/pdf},
	Keywords = {applications, L2, L2 teaching, pronunciation teaching, speech technology},
	Pages = {71-104},
	Publisher = {In Tech},
	Title = {Exploring speech technologies for language learning},
	Url = {http://www.intechopen.com/books/speech-and-language-technologies/exploring-speech-technologies-for-language-learning},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.intechopen.com/books/speech-and-language-technologies/exploring-speech-technologies-for-language-learning}}

Paper  bibtex   

@article{monzon_modulo_1993,
	Author = {Monzón, Luis and Rodríguez Crespo, Miguel Ángel and Escalada, José Gregorio},
	Date = {1993},
	Date-Modified = {2016-09-24 18:56:11 +0000},
	Journal = {Procesamiento del Lenguaje Natural},
	Keywords = {natural language processing, Spanish, speech synthesis, speech technology, syntax, text-to-speech},
	Pages = {367-379},
	Title = {Módulo de análisis sintáctico para un sistema de conversión texto-voz en castellano},
	Url = {http://www.sepln.org/revistaSEPLN/revista/13/13-Todo.pdf},
	Volume = {13},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.sepln.org/revistaSEPLN/revista/13/13-Todo.pdf}}

Paper  bibtex   

@misc{:ac,
	Address = {Madrid},
	Date-Added = {2016-10-05 18:51:15 +0000},
	Date-Modified = {2016-10-19 11:19:58 +0000},
	Keywords = {speech technology, speech synthesis, text-to-speech, text-to-speech system, demo, Spanish},
	Publisher = {Grupo de Tecnología del Habla, Universidad Politécnica de Madrid},
	Read = {1},
	Title = {Speech Technology Group: Concatenative-based samples},
	Url = {http://www-gth.die.upm.es/research/synthesis/concat-samples.html},
	Bdsk-Url-1 = {http://www-gth.die.upm.es/research/synthesis/concat-samples.html}}

@incollection{pastor_pronunciation_2005,
	Address = {Dordrecht},
	Author = {Pastor, Moisés and Casacuberta, Francisco},
	Booktitle = {The integration of phonetic knowledge in speech technology},
	Date = {2005},
	Date-Modified = {2016-09-24 18:56:12 +0000},
	Editor = {Barry, William J and van Dommelen, Wim A},
	Keywords = {phonetic knowledge, speech recognition, speech technology},
	Pages = {133-148},
	Publisher = {Springer},
	Series = {Text, {Speech} and {Language} {Technology}},
	Title = {Pronunciation modeling}}

Paper  doi  abstract   bibtex   

@article{sridhar_enriching_2011,
	Author = {Sridhar, Vivek Kumar Rangarajan and Bangalore, Srinivas and Narayanan, Shrikanth S},
	Date = {2011},
	Date-Modified = {2017-04-19 08:04:09 +0000},
	Doi = {10.1016/j.csl.2011.08.001},
	Issn = {0885-2308},
	Journal = {Computer Speech \& Language},
	Keywords = {linguistic knowledge, phonetic knowledge, speech technology, spoken language translation},
	Number = {In Press, Accepted Manuscript},
	Title = {Enriching machine-mediated speech-to-speech translation using contextual information},
	Url = {http://www.sciencedirect.com/science/article/pii/S0885230811000428},
	Abstract = {Conventional approaches to speech-to-speech (S2S) translation typically ignore key contextual information such as prosody, emphasis, discourse state in the translation process. Capturing and exploiting such contextual information is especially important in machine-mediated S2S translation as it can serve as a complementary knowledge source that can potentially aid the end users in improved understanding and disambiguation. In this work, we present a general framework for integrating rich contextual information in S2S translation. We present novel methodologies for integrating source side context in the form of dialog act (DA) tags, and target side context using prosodic word prominence. We demonstrate the integration of the DA tags in two different statistical translation frameworks, phrase-based translation and a bag-of-words lexical choice model. In addition to producing interpretable DA annotated target language translations, we also obtain significant improvements in terms of automatic evaluation metrics such as lexical selection accuracy and BLEU score. Our experiments also indicate that finer representation of dialog information such as yes-no questions, wh-questions and open questions are the most useful in improving translation quality. For target side enrichment, we employ factored translation models to integrate the assignment and transfer of prosodic word prominence (pitch accents) during translation. The factored translation models provide significant improvement in assignment of correct pitch accents to the target words in comparison with a post-processing approach. Our framework is suitable for integrating any word or utterance level contextual information that can be reliably detected (recognized) from speech and/or text.},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/pii/S0885230811000428},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.csl.2011.08.001}}

Paper  abstract   bibtex   

@incollection{gutierrez_arriola_podemos_2003,
	Address = {Barcelona},
	Author = {Gutiérrez Arriola, Juana María and Montero, Juan Manuel and de Córdoba, Ricardo and Pardo, José Manuel},
	Booktitle = {SEAF 2003. Actas del II Congreso de la Sociedad Española de Acústica Forense},
	Date = {2003},
	Date-Modified = {2016-09-24 18:56:05 +0000},
	Editor = {Hernando, Javier},
	Keywords = {Spanish, speech synthesis, speech technology},
	Pages = {35-46},
	Publisher = {Universitat Politècnica de Catalunya - Sociedad Española de Acústica Forense},
	Title = {¿Podemos imitar la voz de una persona? Técnicas de conversión de hablante},
	Url = {http://www-gth.die.upm.es/research/documentation/AN-39Pod-03.pdf},
	Abstract = {En este artículo presentamos dos técnicas de conversión de hablante y su aplicación a la síntesis multilocutor. La primera de las técnicas se basa en la transformación lineal de los formantes y los anchos de banda. La segunda trata de convertir pronunciaciones codificadas mediante LPC utilizando correspondencia de codebooks. En ambos casos se transforma la curva de tono y se aplican los parámetros de fuente glotal del locutor deseado. Los resultados obtenidos son satisfactorios en ambos casos de forma que la voz transformada se identifica claramente como la del locutor deseado, el problema de estas técnicas es que se necesitan muchos datos (tantos como son necesarios para generar una nueva voz en el sintetizador) para que la transformación sea aceptable.},
	Bdsk-Url-1 = {http://www-gth.die.upm.es/research/documentation/AN-39Pod-03.pdf}}

Paper  bibtex   

@article{fant_speech_1962-1,
	Author = {Fant, Gunnar and Mártony, J},
	Date = {1962},
	Date-Modified = {2016-09-24 18:56:03 +0000},
	Journal = {STL-QPSR. Speech, Music and Hearing - Quarterly Progress and Status Report},
	Keywords = {formant synthesis, speech synthesis, speech technology},
	Number = {2},
	Pages = {18-19},
	Title = {Speech synthesis. Instrumentation for parametric synthesis (OVE II)},
	Url = {http://www.speech.kth.se/prod/publications/files/qpsr/1962/1962_3_2_018-019.pdf},
	Volume = {3},
	Bdsk-Url-1 = {http://www.speech.kth.se/prod/publications/files/qpsr/1962/1962_3_2_018-019.pdf}}

Paper  bibtex   

@inproceedings{alcacer_adquisicion_2004,
	Address = {València},
	Author = {Alcácer, Nieves and Castro, María José and Galiano, Isabel and Granell, Ramón and Grau, Sergio and Griol, David},
	Booktitle = {III Jornadas en Tecnología del Habla},
	Date = {2004},
	Date-Modified = {2016-09-24 18:55:57 +0000},
	Editor = {Sanchis, E},
	Keywords = {corpus, dialogue systems, speech corpus, speech technology},
	Pages = {131-136},
	Publisher = {Universitat Politècnica de València - Red Temática en Tecnologías del Habla},
	Title = {Adquisición de un corpus de diálogo: DIHANA},
	Url = {http://lorien.die.upm.es/~lapiz/rtth/JORNADAS/III/actas3JTH.pdf},
	Bdsk-Url-1 = {http://lorien.die.upm.es/~lapiz/rtth/JORNADAS/III/actas3JTH.pdf}}

Paper  abstract   bibtex   

@incollection{badino_general_2004,
	Author = {Badino, Leonardo and Barolo, Claudia and Quazza, Silvia},
	Booktitle = {ICSLP 2004 - Interspeech 2004. Proceedings of the 8th International Conference on Spoken Language Processing},
	Date = {2004},
	Date-Modified = {2016-09-24 18:55:58 +0000},
	File = {Attachment:files/672/Badino, Barolo, Quazza - 2004 - A general approach to TTS reading of mixed-language texts.pdf:application/pdf},
	Keywords = {phonetics, speech synthesis, speech technology},
	Pages = {849-852},
	Publisher = {Jeju Island, Korea. October 4-8, 2004},
	Title = {A general approach to TTS reading of mixed-language texts},
	Url = {http://www.isca-speech.org/archive/interspeech_2004/i04_0849.html},
	Abstract = {The paper presents the Loquendo TTS approach to mixed- language speech synthesis, offering a range of options to face the various situations where texts may occur in different languages or embedding foreign phrases. The most challenging target is to make a monolingual TTS voice read a foreign language text. The adopted Foreign Pronunciation Strategy here discussed allows mixing phonetic transcriptions of different languages, relying on a Phoneme Mapping algorithm making foreign phoneme sequences pronounceable by monolingual voices. The algorithm extends previous solutions, obtaining a plausible approximated pronunciation. The method is efficient, language independent, entirely phonetics-based and it enables any Loquendo TTS voice to speak all the languages provided by the system.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive/interspeech_2004/i04_0849.html}}

Paper  abstract   bibtex   

@book{beskow_formant_2001,
	Address = {Stockholm},
	Author = {Beskow, Jonas},
	Date = {2001},
	Date-Modified = {2016-09-22 20:24:10 +0000},
	Keywords = {acoustic phonetics, formant synthesis, phonetics, segmental, speech synthesis, speech technology, tool, vowels},
	Publisher = {Centre for Speech Technology, KTH},
	Title = {Formant synthesizer demo},
	Url = {http://www.speech.kth.se/wavesurfer/formant/},
	Abstract = {This application demonstrates formant-based synthesis of vowels in real time, in the spirit of Gunnar Fant's Orator Verbis Electris (OVE-1) synthesizer of 1953.},
	Bdsk-Url-1 = {http://www.speech.kth.se/wavesurfer/formant/}}

@article{villarrubia_productos_2002,
	Author = {Villarrubia, Luis and Garrido, Juan María and Relaño, José and Caminero, Francisco Javier and Escalada, José Gregorio and Rodríguez Gancedo, Mari Carmen and Hernández Gómez, Luis Alfonso},
	Date = {2002},
	Date-Modified = {2016-09-24 18:56:17 +0000},
	Journal = {Comunicaciones de Telefónica I+D},
	Keywords = {Spanish, speech technology},
	Pages = {53-72},
	Title = {Productos de tecnología del habla para Latinoamérica},
	Volume = {27},
	Abstract = {Este artículo presenta los productos de tecnología del habla especializados para el mercado latinoamericano que han sido desarrollados por Telefónica I+D. Se expone la enorme perspectiva de negocio y la gran capacidad de creación de los servicios de voz de alta calidad, adaptados a un ámbito cultural tan importante como las diferentes lenguas y variedades dialectales de Latinoamérica. Es destacable la capacidad actual de Telefónica I+D para la creación de servicios, gracias a haber desarrollado íntegramente tres pilares básicos: los productos de tecnología del habla, las plataformas avanzadas y los grupos de desarrollo multidisciplinares con amplia experiencia. El análisis y la evaluación de los productos de Telefónica I+D para las diferentes variedades del español y portugués de Brasil, muestran una posición de privilegio para el lanzamiento de los servicios de voz. Gracias a la posibilidad de poder disponer de productos avanzados se obtiene un incremento de la calidad y del tráfico generado, y una disminución del coste y tiempo en el desarrollo de los servicios.}}

Paper  bibtex   

@article{rabiner_tutorial_1989,
	Author = {Rabiner, Lawrence R},
	Date = {1989},
	Date-Modified = {2016-09-24 18:56:13 +0000},
	File = {Attachment:files/9360/Rabiner - 1989 - A tutorial on Hidden Markov Models and selected applications in speech recognition.pdf:application/pdf},
	Journal = {Proceedings of the IEEE},
	Keywords = {signal processing, speech recognition, speech technology},
	Number = {2},
	Pages = {257-286},
	Title = {A tutorial on Hidden Markov Models and selected applications in speech recognition},
	Url = {http://www.glyc.dc.uba.ar/agustin/ith-2011/archivos-11/Rabiner_1989.pdf},
	Volume = {77},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.glyc.dc.uba.ar/agustin/ith-2011/archivos-11/Rabiner_1989.pdf}}

Paper  bibtex   

@inproceedings{llisterri_programme_2012,
	Address = {Centre for Speech Technology, Royal Institute of Technology, Stockholm, Sweden. 6-8 June, 2012},
	Author = {Llisterri, Joaquim},
	Booktitle = {IS ADEPT 2012. International Symposium on Automatic Detection of Errors in Pronunciation Training},
	Date = {2012},
	Date-Modified = {2016-09-23 19:24:09 +0000},
	File = {Attachment:files/6900/Llisterri - 2012 - Programme Committee.pdf:application/pdf},
	Keywords = {applications, CV, CV avaluació, CV avaluació congressos, phonetics, speech technology},
	Title = {Programme Committee},
	Url = {http://www.speech.kth.se/isadept/},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.speech.kth.se/isadept/}}

@phdthesis{fodge_introducing_2014,
	Address = {Barcelona},
	Author = {Fodge, Kimber D},
	Date = {2014},
	Date-Modified = {2016-09-23 19:24:05 +0000},
	File = {Attachment:files/3973/Fodge - 2014 - Introducing Spanish dialects in a linguistic processing module for improved ASR and novel speech synthesis capabilities.pdf:application/pdf},
	Keywords = {automatic phonetic transcription, CV, CV citació, CV EIN@, CV tribunal, CV tribunal máster, España, geographical variation, phonetic knowledge, Spanish, speech recognition, speech synthesis, speech technology, text-to-speech, transcription},
	School = {Programa oficial de postgrau "Comunicació lingüística i mediació multilingüe", Departament de Traducció i Ciències del Llenguatge, Universitat Pompeu Fabra},
	Title = {Introducing Spanish dialects in a linguistic processing module for improved ASR and novel speech synthesis capabilities},
	Bdsk-File-1 = {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}}

@article{oshaughnessy_automatic_1983,
	Author = {O'Shaughnessy, Douglas},
	Date = {1983},
	Date-Modified = {2016-09-24 18:56:12 +0000},
	Journal = {IEEE Communications Magazine},
	Keywords = {general, speech synthesis, speech technology},
	Number = {9},
	Pages = {26-34},
	Title = {Automatic speech synthesis},
	Volume = {21}}

@techreport{aguilar_propuesta_1991,
	Address = {Bellaterra},
	Author = {Aguilar, Lourdes},
	Date = {1991},
	Date-Modified = {2016-09-23 19:24:00 +0000},
	File = {Aguilar_1991_Propuesta de un Test de Rimas Modificado para el español.pdf:files/12344/Aguilar_1991_Propuesta de un Test de Rimas Modificado para el español.pdf:application/pdf},
	Institution = {Universitat Autònoma de Barcelona},
	Keywords = {assessment, Spanish, speech synthesis, speech technology, text-to-speech},
	Title = {Propuesta de un Test de Rimas Modificado para el español},
	Bdsk-File-1 = {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}}

@article{murray_toward_1993,
	Author = {Murray, Iain R and Arnott, John L},
	Date = {1993},
	Date-Modified = {2017-04-19 08:04:08 +0000},
	Doi = {10.1121/1.405558},
	File = {Attachment:files/8265/Murray, Arnott - 1993 - Toward the simulation of emotion in synthetic speech A review of the literature on human vocal emotion.pdf:application/pdf},
	Journal = {The Journal of the Acoustical Society of America},
	Keywords = {emotions, speaking styles, speech synthesis, speech technology},
	Number = {2},
	Pages = {1097-1108},
	Title = {Toward the simulation of emotion in synthetic speech: A review of the literature on human vocal emotion},
	Volume = {93},
	Abstract = {There has been considerable research into perceptible correlates of emotional state, but a very limited amount of the literature examines the acoustic correlates and other relevant aspects of emotion effects in human speech; in addition, the vocal emotion literature is almost totally separate from the main body of speech analysis literature. A discussion of the literature describing human vocal emotion, and its principal findings, are presented. The voice parameters affected by emotion are found to be of three main types: voice quality, utterance timing, and utterance pitch contour. These parameters are described both in general and in detail for a range of specific emotions. Current speech synthesizer technology is such that many of the parameters of human speech affected by emotion could be manipulated systematically in synthetic speech to produce a simulation of vocal emotion; application of the literature to construction of a system capable of producing synthetic speech with emotion is discussed.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://dx.doi.org/10.1121/1.405558}}

Paper  doi  abstract   bibtex   

@article{campillo_integrating_2009,
	Author = {Campillo, Francisco and van Santen, Jan P H and Rodríguez Banga, Eduardo},
	Date = {2009},
	Date-Modified = {2017-04-19 08:04:06 +0000},
	Doi = {10.1016/j.specom.2009.01.007},
	Journal = {Speech Communication},
	Keywords = {phonetics, speech synthesis, speech technology},
	Number = {5},
	Pages = {452-465},
	Title = {Integrating phrasing and intonation modelling using syntactic and morphosyntactic information},
	Url = {http://dx.doi.org/10.1016/j.specom.2009.01.007},
	Volume = {51},
	Abstract = {This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75\% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5\% of sentences were rated as worse or much worse.},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.specom.2009.01.007}}

@article{privat_etude_2004,
	Author = {Privat, R and Vigouroux, Nadine and Truillet, P},
	Date = {2004},
	Date-Modified = {2016-09-24 18:56:13 +0000},
	Journal = {Revue PArole},
	Keywords = {accessibility, age, clinical, interspeaker variation, speech recognition, speech technology},
	Pages = {281-318},
	Title = {Étude de l'effet du vieillissement dur les productions langagières et sur les performances en reconnaissance automatique de la parole},
	Volume = {31-32}}

Paper  bibtex   

@book{Medialink--Nuance:2006aa,
	Author = {{Medialink \& Nuance}},
	Date = {2006},
	Date-Modified = {2017-04-01 10:22:25 +0000},
	Keywords = {applications, speech recognition, speech technology},
	Publisher = {Kurzweil},
	Title = {Nuance host "The Amazing Race" - text messaging and speech recognition competition, pits man against machine},
	Url = {http://www.kurzweilai.net/nuance-hosts-amazing-race-text-speech-competition},
	Bdsk-Url-1 = {http://www.kurzweilai.net/nuance-hosts-amazing-race-text-speech-competition}}

@book{tur_spoken_2011,
	Address = {Oxford},
	Date = {2011},
	Date-Modified = {2016-09-22 20:24:47 +0000},
	Editor = {Tur, Gokhan and de Mori, Renato},
	Isbn = {978-0-470-68824-3},
	Keywords = {language technology, speech technology, spoken language understanding},
	Publisher = {John Wiley \& Sons},
	Title = {Spoken language understanding: systems for extracting semantic information from speech},
	Abstract = {Forward. Preface. 1 Introduction (Gokhan Tur and Renato De Mori). 1.1 A Brief History of Spoken Language Understanding. 1.2 Organization of the Book. Conversations. References. PART ONE SPOKEN LANGUAGE UNDERSTANDING FOR HUMAN/MACHINE INTERACTIONS. 2 History of Knowledge and Processes for Spoken Language Understanding (Renato De Mori). 2.1 Introduction. 2.2 Meaning Representation and Sentence Interpretation. 2.3 Knowledge Fragments and Semantic Composition. 2.4 Probabilistic Interpretation in SLU Systems. 2.5 Interpretation with Partial Syntactic Analysis. 2.6 Classification Models for Interpretation. 2.7 Advanced Methods and Resources for Semantic Modeling and Interpretation. 2.8 Recent Systems. 2.9 Conclusions. References. 3 Semantic Frame-based Spoken Language Understanding (Ye-Yi Wang, Li Deng and Alex Acero). 3.1 Background. 3.2 Knowledge-based Solutions. 3.3 Data-driven Approaches. 3.4 Summary. References. 4 Intent Determination and Spoken Utterance Classification (Gokhan Tur and Li Deng). 4.1 Background. 4.2 Task Description. 4.3 Technical Challenges. 4.4 Benchmark Data Sets. 4.5 Evaluation Metrics. 4.6 Technical Approaches. 4.7 Discussion and Conclusions. References. 5 Voice Search (Ye-Yi Wang, Dong Yu, Yun-Cheng Ju and Alex Acero). 5.1 Background. 5.2 Technology Review. 5.3 Summary. References. 6 Spoken Question Answering (Sophie Rosset, Olivier Galibert and Lori Lamel). 6.1 Introduction. 6.2 Specific Aspects of Handling Speech in QA Systems. 6.3 QA Evaluation Campaigns. 6.4 Question-answering Systems. 6.5 Projects Integrating Spoken Requests and Question Answering. 6.6 Conclusions. References. 7 SLU in Commercial and Research Spoken Dialogue Systems (David Suendermann and Roberto Pieraccini). 7.1 Why Spoken Dialogue Systems (Do Not) Have to Understand. 7.2 Approaches to SLU for Dialogue Systems. 7.3 From Call Flow to POMDP: How Dialogue Management Integrates with SLU. 7.4 Benchmark Projects and Data Sets. 7.5 Time is Money: The Relationship between SLU and Overall Dialogue System Performance. 7.6 Conclusion. References. 8 Active Learning (Dilek Hakkani-Tür and Giuseppe Riccardi). 8.1 Introduction. 8.2 Motivation. 8.3 Learning Architectures. 8.4 Active Learning Methods. 8.5 Combining Active Learning with Semi-supervised Learning. 8.6 Applications. 8.7 Evaluation of Active Learning Methods. 8.8 Discussion and Conclusions. References. II SPOKEN LANGUAGE UNDERSTANDING FOR HUMAN/HUMAN CONVERSATIONS. 9 Human/Human Conversation Understanding (Gokhan Tur and Dilek Hakkani-Tür). 9.1 Background. 9.2 Human/Human Conversation Understanding Tasks. 9.3 Dialogue Act Segmentation and Tagging. 9.4 Action Item and Decision Detection. 9.5 Addressee Detection and Co-reference Resolution. 9.6 Hot Spot Detection. 9.7 Subjectivity, Sentiment, and Opinion Detection. 9.8 Speaker Role Detection. 9.9 Modeling Dominance. 9.10 Argument Diagramming. 9.11 Discussion and Conclusions. References. 10 Named Entity Recognition (Frédéric Béchet). 10.1 Task Description. 10.2 Challenges Using Speech Input. 10.3 Benchmark Data Sets, Applications. 10.4 Evaluation Metrics. 10.5 Main Approaches for Extracting NEs from Text. 10.6 Comparative Methods for NER from Speech. 10.7 New Trends in NER from Speech. 10.8 Conclusions. References. 11 Topic Segmentation (Matthew Purver). 11.1 Task Description. 11.2 Basic Approaches, and the Challenge of Speech. 11.3 Applications and Benchmark Datasets. 11.4 Evaluation Metrics. 11.5 Technical Approaches. 11.6 New Trends and Future Directions. References. 12 Topic Identification (Timothy J. Hazen). 12.1 Task Description. 12.2 Challenges Using Speech Input. 12.3 Applications and Benchmark Tasks. 12.4 Evaluation Metrics. 12.5 Technical Approaches. 12.6 New Trends and Future Directions. References. 13 Speech Summarization (Yang Liu and Dilek Hakkani-Tür). 13.1 Task Description. 13.2 Challenges when Using Speech Input. 13.3 Data Sets. 13.4 Broadcast News (BN). 13.5 Evaluation Metrics. 13.6 General Approaches. 13.7 More Discussions on Speech versus Text Summarization. 13.8 Conclusions. References. 14 Speech Analytics (I. Dan Melamed and Mazin Gilbert 14.1 Introduction. 14.2 System Architecture. 14.3 Speech Transcription. 14.4 Text Feature Extraction. 14.5 Acoustic Feature Extraction. 14.6 Relational Feature Extraction. 14.7 DBMS. 14.8 Media Server and Player. 14.9 Trend Analysis. 14.10 Alerting System. 14.11 Conclusion. References. 15 Speech Retrieval (Ciprian Chelba, Timothy J. Hazen, Bhuvana Ramabhadran and Murat Saraςlar). 15.1 Task Description. 15.2 Applications. 15.3 Challenges Using Speech Input. 15.4 Evaluation Metrics. 15.5 Benchmark Data Sets. 15.6 Approaches. 15.7 New Trends. 15.8 Discussion and Conclusions. References. Index.}}

@incollection{fant_acoustic_2004,
	Address = {Dordrecht},
	Author = {Fant, Gunnar},
	Booktitle = {Speech acoustics and phonetics: Selected writings},
	Date = {2004},
	Date-Modified = {2016-09-24 18:56:03 +0000},
	Keywords = {acoustic phonetics, phonetics, speech synthesis, speech technology},
	Pages = {18-28},
	Publisher = {Kluwer},
	Title = {Acoustic analysis and synthesis of speech with applications to Swedish (Excerpts)}}

Paper  bibtex   

@inproceedings{escudero_corpus_2002,
	Address = {Orlando, Florida, May 13-17, 2002},
	Author = {Escudero, David and Cardeñoso, Valentín and Bonafonte, Antonio},
	Booktitle = {ICASSP 2002. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing},
	Date = {2002},
	Date-Modified = {2017-05-17 19:40:49 +0000},
	Keywords = {lexical stress, phonetics, prosody, Spanish, speech synthesis, speech technology, stress group, text-to-speech, unit selection, FFLE},
	Pages = {481-484},
	Title = {Corpus based extraction of quantitative prosodic parameters of stress groups in Spanish},
	Url = {http://gps-tsc.upc.es/veu/research/pubs/download/esc_pro_02.pdf},
	Bdsk-File-1 = {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}}

@incollection{flanagan_speech_1984,
	Address = {Dordrecht},
	Author = {Flanagan, James L},
	Booktitle = {ICPhS 1984. Proceedings of the 10th International Congress of Phonetic Sciences},
	Date = {1984},
	Date-Modified = {2016-09-24 18:56:03 +0000},
	Editor = {van den Broecke, Marcel P R and Cohen, Antoine},
	Keywords = {history, speech technology},
	Pages = {121-124},
	Publisher = {Foris},
	Title = {Speech technology in the coming decades}}

@incollection{denecke_does_2008,
	Address = {Dordrecht},
	Author = {Denecke, Matthias and Yasuda, Norihito},
	Booktitle = {Recent Trends in Discourse and Dialogue},
	Date = {2008},
	Date-Modified = {2016-09-24 18:56:02 +0000},
	Editor = {Dybkjaer, Laila and Minker, Wolfgang},
	Keywords = {dialogue systems, speech technology},
	Pages = {219-246},
	Publisher = {Springer},
	Series = {39},
	Title = {Does this answer your question?}}

@incollection{abe_speaking_1997,
	Address = {New York},
	Author = {Abe, M},
	Booktitle = {Progress in speech synthesis},
	Date = {1997},
	Date-Modified = {2016-09-24 18:55:57 +0000},
	Editor = {van Santen, J P H and Sproat, R W and Hirschberg, J},
	Keywords = {speaking styles, speech synthesis, speech technology},
	Pages = {495-510},
	Publisher = {Springer},
	Title = {Speaking styles: Statistical analysis and synthesis by a Text-to-Speech system}}

Paper  bibtex   

@book{llisterri_corpus_2013,
	Address = {Laboratorio de Fonética, Instituto de Lengua, Literatura y Antropología, Centro de Ciencias Humanas y Sociales, Consejo Superior de Investigaciones Científicas. Madrid, 27-29 de maig de 2013},
	Author = {Llisterri, Joaquim},
	Date = {2013},
	Date-Modified = {2016-09-28 09:40:15 +0000},
	Keywords = {corpus, CV, CV cursos, CV cursos externs, CV cursos postgrau, CV cursos postgrau externs, CV cursos postgrau POPEF, language resources, speech corpora, speech technology},
	Publisher = {Máster en Fonética y Fonología, Programa Oficial de Posgrado en Estudios Fónicos},
	Title = {Corpus orales para las tecnologías del habla (2012-2013)},
	Url = {http://liceu.uab.cat/~joaquim/language_resources/MFF_12/MFF_12.html},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/language_resources/MFF_12/MFF_12.html}}

Paper  bibtex   

@incollection{jurafsky_chapter_2009,
	Address = {Upper Saddle River, NJ},
	Author = {Jurafsky, Dan and Martin, James H},
	Booktitle = {Speech and language processing. An introduction to natural language processing, computational linguistics, and speech recognition},
	Date = {2009},
	Date-Modified = {2017-04-04 10:07:42 +0000},
	Edition = {2},
	File = {Attachment:files/5811/Jurafsky, Martin - 2009 - Chapter 8 Speech synthesis.pdf:application/pdf},
	Keywords = {speech synthesis, speech technology, textbook},
	Publisher = {Prentice Hall},
	Title = {Chapter 8: Speech synthesis},
	Url = {http://www.cs.colorado.edu/~martin/slp2.html},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.cs.colorado.edu/~martin/slp2.html}}

Paper  bibtex   

@book{tomasco_ibm_2007,
	Author = {Tomasco, Steve},
	Date = {2007},
	Date-Modified = {2016-09-23 19:24:14 +0000},
	Keywords = {accessibility, sign language, speech technology},
	Title = {IBM Voice-to-Sign Language Translation Tech},
	Url = {https://www.youtube.com/watch?v=RarMKnjqzZU},
	Bdsk-Url-1 = {https://www.youtube.com/watch?v=RarMKnjqzZU}}

@article{zhang_cognitive_2006,
	Author = {Zhang, Tong and Hasegawa-Johnson, Mark A and Levinson, Stephen E},
	Date = {2006},
	Date-Modified = {2017-04-19 08:04:09 +0000},
	Doi = {10.1016/j.specom.2005.09.006},
	File = {Attachment:files/11967/Zhang, Hasegawa-Johnson, Levinson - 2006 - Cognitive state classification in a spoken tutorial dialogue system.pdf:application/pdf},
	Journal = {Speech Communication},
	Keywords = {applications, dialogue systems, emotions, speaking styles, speech technology},
	Number = {6},
	Pages = {616-632},
	Title = {Cognitive state classification in a spoken tutorial dialogue system},
	Volume = {48},
	Abstract = {This paper addresses the manual and automatic labelling, from spontaneous speech, of a particular type of user affect that we call the cognitive state in a tutorial dialogue system with students of primary and early middle school ages. Our definition of the cognitive state is based on analysis of children's spontaneous speech, which is acquired during Wizard-of-Oz simulations of an intelligent math and physics tutor. The cognitive states of children are categorized into three classes: confidence, puzzlement, and hesitation. The manual labelling of cognitive states had an inter-transcriber agreement of kappa score 0.93. The automatic cognitive state labels are generated by classifying prosodic features, text features, and spectral features. Text features are generated from an automatic speech recognition (ASR) system; features include indicator functions of keyword classes and part-of-speech sequences. Spectral features are created based on acoustic likelihood scores of a cognitive state-dependent ASR system, in which phoneme models are adapted to utterances labelled for a particular cognitive state. The effectiveness of the proposed method has been tested on both manually and automatically transcribed speech, and the test yielded very high correctness: 96.6\% for manually transcribed speech and 95.7\% for automatically recognized speech. Our study shows that the proposed spectral features greatly outperformed the other types of features in the cognitive state classification experiments. Our study also shows that the spectral and prosodic features derived directly from speech signals were very robust to speech recognition errors, much more than the lexical and part-of-speech based features.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.specom.2005.09.006}}

Paper  bibtex   

@inproceedings{Yarowsky:1994aa,
	Address = {Las Cruces, NM, USA. 27-30 June, 1994},
	Author = {Yarowsky, David},
	Booktitle = {32nd Annual Meeting of the Association for Computational Linguistics},
	Date = {1994},
	Date-Added = {2017-04-03 18:29:38 +0000},
	Date-Modified = {2017-04-10 08:54:31 +0000},
	Keywords = {French, language technology, lexical stress, linguistic processing, natural language processing, phonetics, prosody, Spanish, speech synthesis, speech technology, suprasegmental transcription, text pre-processing, text-to-speech, transcription},
	Pages = {89-95},
	Title = {Decision lists for lexical ambiguity resolution: Application to accent restoration in Spanish and Frenc},
	Url = {http://aclweb.org/anthology/P94-1013},
	Bdsk-File-1 = {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}}

Paper  abstract   bibtex   

@book{bunnell_simplified_1999,
	Address = {Wilmington, DE},
	Author = {Bunnell, H Timothy},
	Date = {1999},
	Date-Modified = {2016-09-23 19:24:01 +0000},
	Keywords = {acoustic phonetics, consonants, formant synthesis, phonetics, segmental, speech synthesis, speech technology, tool, vowels},
	Publisher = {Speech Research Lab, A.I duPont Hospital for Children and the University of Delaware},
	Title = {Simplified CV syllable synthesis},
	Url = {http://www.asel.udel.edu/speech/tutorials/synthesis/ceevees.html},
	Abstract = {This interface allows you to synthesize many English consonants in CV syllable context using the Klatt synthesizer.},
	Bdsk-Url-1 = {http://www.asel.udel.edu/speech/tutorials/synthesis/ceevees.html}}

Paper  bibtex   

@inproceedings{llisterri_tecnologias_2002,
	Address = {Santiago de Compostela},
	Author = {Llisterri, Joaquim},
	Booktitle = {Actas da VIII Conferencia Internacional de Linguas Minoritarias. Pol{\'i}ticas ling{\"u}{\'i}sticas e educativas na Europa Comunitaria},
	Date = {2002},
	Date-Modified = {2016-09-24 18:56:09 +0000},
	Editor = {Bugar{\'i}n, Mar{\'i}a Xes{\'u}s and Cajide, Jos{\'e} and Dosil, Agust{\'i}n and Ferreiro, Xavier and Gonz{\'a}lez Gonz{\'a}lez, Manuel and Santos, Miguel Anxo},
	Isbn = {84-453-3465-4},
	Keywords = {Catalan, CV, CV publicacions, CV publicacions actes congressos, speech technology},
	Language = {es},
	Pages = {163-169},
	Publisher = {Xunta de Galicia},
	Title = {Las tecnolog{\'i}as del habla en lengua catalana},
	Url = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_02_TecnolHabla_Catalan.pdf},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/publicacions/Llisterri_02_TecnolHabla_Catalan.pdf}}

Paper  abstract   bibtex   

@article{farrus_fusing_2009,
	Author = {Farrús, Mireia},
	Date = {2009},
	Date-Modified = {2016-09-24 18:56:03 +0000},
	Journal = {International Journal of Speech, Language and the Law},
	Keywords = {forensic, forensic phonetics, phonetic knowledge, phonetics, prosody, speaker recognition, speech technology},
	Number = {1},
	Pages = {169-171},
	Title = {Fusing prosodic and acoustic information for speaker recognition},
	Url = {http://www.equinoxjournals.com/ojs/index.php/IJSLL/article/view/6329/4892},
	Volume = {16},
	Abstract = {Automatic speaker recognition is the use of a machine to identify an individual from a spoken sentence. Recently, this technology has been undergone an increasing use in applications such as access control, transaction authentication, law enforcement, forensics, and system customisation, among others. One of the central questions addressed by this eld is what is it in the speech signal that con-veys speaker identity. Traditionally, automatic speaker recognition systems have relied mostly on short-term features related to the spectrum of the voice. However, human speaker recognition relies on other sources of information; therefore, there is reason to believe that these sources can play also an important role in the automatic speaker recognition task, adding complemen-tary knowledge to the traditional spectrum-based recognition systems and thus improving their accuracy. The main objective of this thesis is to add prosodic information to a traditional spectral system in order to improve its performance. To this end, several characteristics related to human speech prosody {\textbar}which is conveyed through intonation, rhythm and stress{\textbar} are selected and combined with the existing spectral features. Furthermore, this thesis also focuses on the use of additional acoustic features {\textbar}namely jitter and shimmer{\textbar} to improve the performance of the proposed spectral-prosodic verication system. Both features are related to the shape and dimension of the vocal tract, and they have been largely used to detect voice pathologies. Since almost all the above-mentioned applications can be used in a multimodal environment, this thesis also aims to combine the voice features used in the speaker recognition system together with other biometric identiers {\textbar}face{\textbar} in order to improve the global performance. To this end, several normalisation and fusion techniques are used, and the nal fusion results are improved by applying dierent fusion strategies based on sequences of several steps. Furthermore, multimodal fusion is also improved by applying a histogram equalisation to the unimodal score distributions as a normalisation technique. On the other hand, it is well know that humans are able to identify others from voice even when their voices are disguised. The question arises as to how vulnerable automatic speaker recognition systems are against dierent voice disguises, such as human imitation or articial voice conversion, which are potential threats to security systems that rely on automatic speaker recognition. The last part of this thesis consists of an analysis of the robustness of such systems against human voice imitations and synthetic converted voices, and the inuence of foreign accents and dialects {\textbar}as a sort of imitation{\textbar} in auditory speaker recognition.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.equinoxjournals.com/ojs/index.php/IJSLL/article/view/6329/4892}}

@incollection{dutoit_text--speech_2003,
	Address = {Oxford},
	Author = {Dutoit, Thierry and Stylianou, Yannis},
	Booktitle = {The Oxford handbook of computational linguistics},
	Date = {2003},
	Date-Modified = {2016-09-24 18:56:02 +0000},
	Editor = {Mitkov, R},
	Keywords = {speech synthesis, speech technology, text-to-speech},
	Pages = {323-338},
	Publisher = {Oxford University Press},
	Title = {Text-to-speech synthesis}}

Paper  abstract   bibtex   

@article{campbell_developments_2005,
	Author = {Campbell, Nick},
	Date = {2005},
	Date-Modified = {2016-09-24 18:56:00 +0000},
	File = {Attachment:files/1849/Campbell - 2005 - Developments in corpus-based speech synthesis Approaching natural conversational speech.pdf:application/pdf},
	Journal = {IEICE Transactions on Information and Systems},
	Keywords = {speaking styles, speech synthesis, speech technology},
	Number = {3},
	Pages = {376-383},
	Title = {Developments in corpus-based speech synthesis: Approaching natural conversational speech},
	Url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.8099&rep=rep1&type=pdf},
	Volume = {E88-D},
	Abstract = {This paper describes the special demands of conversational speech in the context of corpus-based speech synthesis. The author proposed the CHATR system of prosody-based unit-selection for concatenative waveform synthesis seven years ago, and now extends this work to incorporate the results of an analysis of five-years of recordings of spontaneous conversational speeech in a wide range of actual daily-life situations. The paper proposes that the expresion of affect (often translated as `kansei' in Japanese) is the main factor differentiating laboratory speech from realworld conversational speech, and presents a framework for the specification of affect through differences in speaking style and voice quality. Having an enormous corpus of speech samples available for concatenation allows the selection of complete phrase-sized utterance segments, and changes the focus of unit selection from segmental or phonetic continuity to one of prosodic and discoursal appropriateness instead. Samples of the resulting large-corpus-based synthesis can be heard at http://feast.his.atr.jp/AESOP.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.8099&rep=rep1&type=pdf}}

Paper  bibtex   

@techreport{_ssw2-1994._1994,
	Address = {Mohonk Mountain House, New Paltz, NY, USA, September 12-15, 1994},
	Date = {1994},
	Date-Modified = {2016-11-06 18:35:55 +0000},
	Keywords = {proceedings, speech synthesis, speech technology},
	Title = {SSW2-1994. Proceedings of the Second ESCA/IEEE Workshop on Speech Synthesis},
	Url = {http://www.isca-speech.org/archive_open/ssw2/index.html},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive_open/ssw2/index.html}}

@book{dybkjaer_evaluation_2007,
	Address = {Dordrecht},
	Date = {2007},
	Date-Modified = {2016-09-22 20:24:45 +0000},
	Editor = {Dybkjaer, Laila and Hemsen, H and Minker, Wolfgang},
	File = {Attachment:files/3277/Unknown - 2007 - Evaluation of text and speech systems.pdf:application/pdf},
	Keywords = {assessment, language technology, natural language processing, speech technology},
	Publisher = {Springer},
	Title = {Evaluation of text and speech systems},
	Bdsk-File-1 = {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}}

@incollection{de_oliveira_dixi:_1993,
	Address = {Lisboa},
	Author = {de Oliveira, Luís Caldas and Viana, Maria do Céu and Trancoso, Isabel},
	Booktitle = {EPLP 1993. Actas do 1o Encontro de Processamento da Língua Portuguesa Escrita e Falada},
	Date = {1993},
	Date-Modified = {2016-09-24 18:56:12 +0000},
	Keywords = {Portuguese, speech synthesis, speech technology},
	Pages = {153-158},
	Publisher = {INESC},
	Title = {DIXI: Sistema de síntese de fala a partir de texto para o portuguës}}

Paper  abstract   bibtex   

@article{marin_elaboracion_2001,
	Author = {Marín, Rafael and Aguilar, Lourdes},
	Date = {2001},
	Date-Modified = {2016-09-24 18:56:10 +0000},
	Journal = {RESLA. Revista Española de Lingüística Aplicada},
	Keywords = {phonetics, Spanish, speech synthesis, speech technology, text-to-speech},
	Pages = {7-22},
	Title = {La elaboración de un diccionario de unidades acústicas para la síntesis del habla. Una aproximación metodológica},
	Url = {http://dialnet.unirioja.es/servlet/articulo?codigo=871276},
	Volume = {14},
	Abstract = {Un sistema de conversión de texto a habla requiere el diseño y la conexión de módulos de procesamiento lingüístico y de tratamiento de señal. En aquellos sistemas basados en la concatenación de segmentos de voz, la calidad de la voz resultante depende en buena medida del diseño del diccionario de unidades acústicas que se han grabado y almacenado. En este trabajo se presentan las opciones metodológicas utilizadas más comúnmente en la constitución de un inventario de unidades acústicas para la síntesis de habla. Las etapas (definición de las unidades de síntesis, diseño del corpus de grabación, selección del locutor) se abordan teniendo en cuenta la descripción del sistema fonético y fonológico del español, de tal modo que se demuestra que aunque sea una tarea eminentemente aplicada debe conjugarse con la reflexión teórica.},
	Bdsk-Url-1 = {http://dialnet.unirioja.es/servlet/articulo?codigo=871276}}

Paper  bibtex   

@phdthesis{lemmetty_review_1999,
	Address = {Helsinki},
	Author = {Lemmetty, S},
	Date = {1999},
	Date-Modified = {2016-09-22 20:24:27 +0000},
	File = {Attachment:files/6467/Lemmetty - 1999 - Review of speech synthesis technology.pdf:application/pdf},
	Keywords = {general, speech synthesis, speech technology},
	School = {Helsinki University of Technology},
	Title = {Review of speech synthesis technology},
	Url = {http://www.acoustics.hut.fi/publications/files/theses/lemmetty_mst/index.html},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.acoustics.hut.fi/publications/files/theses/lemmetty_mst/index.html}}

Paper  bibtex   

@book{cendrowski_beta_2012,
	Author = {Cendrowski, Mark},
	Date = {2012},
	Date-Modified = {2016-09-23 19:24:02 +0000},
	Keywords = {speech technology, video},
	Publisher = {Chuck Lorre Productions, Warner Bros Television},
	Title = {The Beta Test Initiation, The Big Bang Theory, Season 5, Episode 14},
	Url = {https://www.youtube.com/watch?v=WXqRmBrBboA},
	Bdsk-Url-1 = {https://www.youtube.com/watch?v=WXqRmBrBboA}}

@incollection{paulus_guidelines_2000,
	Address = {Frankfurt am Main},
	Author = {Paulus, E},
	Booktitle = {Speech and signals. Aspects of speech synthesis and automatic speech recognition. Dedicated to Wolfgang Hess on his 60th birthday},
	Date = {2000},
	Date-Modified = {2016-09-24 18:56:13 +0000},
	Editor = {Sendlmeier, W F},
	Keywords = {assessment, speech recognition, speech technology},
	Pages = {129-139},
	Publisher = {Hector},
	Title = {Some guidelines for the evaluation of approaches to automatic speech recognition}}

@book{meloni_fondements_1996,
	Address = {Paris},
	Date = {1996},
	Date-Modified = {2016-09-22 20:24:46 +0000},
	Editor = {Méloni, H},
	Keywords = {compilation, speech technology, textbook},
	Publisher = {AUPELF - UREF},
	Title = {Fondements et perspectives en traitement automatique de la parole}}

Paper  doi  abstract   bibtex   

@article{noth_use_2002,
	Author = {Nöth, Elmar and Batliner, Anton and Warnke, V and Haas, Jürgen and Boros, M and Buckow, J and Huber, R and Gallwitz, F and Nutt, M and Niemann, H},
	Date = {2002},
	Date-Modified = {2017-04-19 08:04:08 +0000},
	Doi = {10.1016/S0167-6393(01)00025-5},
	Issn = {01676393},
	Journal = {Speech Communication},
	Keywords = {dialogue systems, phonetics, prosody, speech technology},
	Month = jan,
	Number = {1-2},
	Pages = {45-62},
	Title = {On the use of prosody in automatic dialogue understanding},
	Url = {http://linkinghub.elsevier.com/retrieve/pii/S0167639301000255},
	Volume = {36},
	Abstract = {In this paper, we show how prosodic information can be used in automatic dialogue systems and give some examples of promising new approaches. Most of these examples are taken from our own work in the V speech-to-speech translation system and in the EVAR train timetable dialogue system. In a `prosodic orbit', we first present units, phenomena, annotations and statistical methods from the signal (acoustics) to the dialogue understanding phase. We show then, how prosody can be used together with other knowledge sources for the task of resegmentation if a first segmentation turns out to be wrong, and how an integrated approach leads to better results than a sequential use of the different knowledge sources; then we present a hybrid approach which is used to perform a shallow parsing and which uses prosody to guide the parsing; finally, we show how a critical system evaluation can help to improve the overall performance of automatic dialogue systems.},
	Bdsk-Url-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0167639301000255},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/S0167-6393(01)00025-5}}

Paper  abstract   bibtex   

@phdthesis{trilla_natural_2010,
	Author = {Trilla, Alexandre},
	Date = {2010},
	Date-Modified = {2016-09-23 19:24:14 +0000},
	File = {Attachment:files/11180/Trilla - 2010 - Natural Language Processing techniques applied to speech technologies.pdf:application/pdf},
	Keywords = {emotions, language technology, linguistic processing, natural language processing, speaking styles, speech synthesis, speech technology, text pre-processing, text-to-speech},
	School = {Universitat Ramon Llull},
	Title = {Natural Language Processing techniques applied to speech technologies},
	Url = {http://atrilla.net/data/files/dea_atrilla.pdf},
	Abstract = {This dissertation relates a first research stage in the pursuit of the Ph.D. degree in "Information and communication Technologies and its Management" at La Salle  Universitat Ramon Llull. The dissertation presents an overview of the various approaches to Text- based Sentiment Prediction in order to reveal their effectiveness in the tripartite sentiment recognition task, i.e., the identification of positive, negative and neutral orientations in text. It discusses the application of the bases that support these diverse proposals, from the feature extraction stage to the classification phase, contrasting the contributions that each method yields through a set of experiments with the Semeval 2007 dataset and the Fifty Word Fiction corpus.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://atrilla.net/data/files/dea_atrilla.pdf}}

Paper  bibtex   

@book{_ieee_1993,
	Address = {Piscataway, NJ},
	Date = {1993},
	Date-Modified = {2016-09-23 19:24:16 +0000},
	Keywords = {journal, speech technology},
	Publisher = {IEEE Signal Processing Society},
	Title = {IEEE Transactions on Speech and Audio Processing},
	Url = {http://ieeexplore.ieee.org/servlet/opac?punumber=89},
	Bdsk-Url-1 = {http://ieeexplore.ieee.org/servlet/opac?punumber=89}}

Paper  bibtex   

@book{esign_esign_????-1,
	Address = {Hamburg},
	Author = {{ESIGN}},
	Date-Modified = {2016-09-23 19:24:05 +0000},
	Keywords = {accessibility, dialogue systems, project, sign language, speech technology},
	Publisher = {Institute of German Sign Language and Communication of the Deaf, University of Hamburg},
	Title = {eSIGN, Essential Sign Language Information on Government Newtworks},
	Url = {http://www.sign-lang.uni-hamburg.de/esign/ http://www.sign-lang.uni-hamburg.de/esign/demo.html},
	Bdsk-Url-1 = {http://www.sign-lang.uni-hamburg.de/esign/%20http://www.sign-lang.uni-hamburg.de/esign/demo.html}}

Paper  bibtex   

@misc{Dutoit:2005aa,
	Address = {Mons},
	Author = {Dutoit, Thierry},
	Date = {2005},
	Date-Added = {2016-10-05 19:22:59 +0000},
	Date-Modified = {2017-04-17 12:37:36 +0000},
	Generator = {Internet Assistant for Word 1.00},
	Keywords = {speech technology, speech synthesis, MBROLA},
	Publisher = {TCTS Lab (Théorie des Circuits et Traitement du Signal), Faculté Polytechnique de Mons},
	Read = {1},
	Title = {The MBROLA Project},
	Url = {http://tcts.fpms.ac.be/synthesis/mbrola.html},
	Bdsk-Url-1 = {http://tcts.fpms.ac.be/synthesis/mbrola.html}}

Paper  bibtex   

@book{llisterri_conocimiento_2009,
	Address = {Laboratorio de Fonética, Instituto de Lengua, Literatura y Antropología, Centro de Ciencias Humanas y Sociales, Consejo Superior de Investigaciones Científicas. Madrid, 11-14 de maig de 2009},
	Author = {Llisterri, Joaquim},
	Date = {2009},
	Date-Modified = {2016-09-28 09:41:26 +0000},
	Keywords = {CV, CV cursos, CV cursos externs, CV cursos postgrau, CV cursos postgrau externs, CV cursos postgrau POPEF, phonetic knowledge, speech technology},
	Publisher = {Máster en Fonética y Fonología, Programa Oficial de Posgrado en Estudios Fónicos},
	Title = {Conocimiento fonético y tecnologías del habla (2008-2009)},
	Url = {http://liceu.uab.cat/~joaquim/speech_technology/MFF_08/MFF_08.html},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/speech_technology/MFF_08/MFF_08.html}}

Paper  bibtex   

@inproceedings{casacuberta_development_1991,
	Address = {Chiavari, Italy. September 26-28, 1991},
	Author = {Casacuberta, Francisco and Garc{\'i}a, Ram{\'o}n and Llisterri, Joaquim and Nadeu, Climent and Pardo, Jos{\'e} Manuel and Rubio Ayuso, Antonio J},
	Booktitle = {Proceedings of the workshop on international cooperation and standardization of speech databases and speech I /O assessment methods},
	Date = {1991},
	Date-Modified = {2016-09-23 19:24:02 +0000},
	Editor = {Castagneri, G},
	Keywords = {corpus, CV, CV publicacions, CV publicacions actes congressos, CV xarxes liceu, language resources, phonetics, Spanish, speech corpus, speech technology},
	Language = {en},
	Title = {Development of Spanish corpora for speech research (Albayz{\'i}n)},
	Url = {http://liceu.uab.cat/~joaquim/publicacions/Casacuberta_et_al_91.pdf},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://liceu.uab.cat/~joaquim/publicacions/Casacuberta_et_al_91.pdf}}

Paper  abstract   bibtex   

@article{anusuya_speech_2009,
	Author = {Anusuya, M A and Katti, S K},
	Date = {2009},
	Date-Modified = {2016-09-24 18:55:58 +0000},
	File = {Attachment:files/450/Anusuya, Katti - 2009 - Speech recognition by machine A review.pdf:application/pdf},
	Journal = {International Journal of Computer Science and Information Society},
	Keywords = {general, speech recognition, speech technology},
	Number = {3},
	Pages = {181-205},
	Title = {Speech recognition by machine: A review},
	Url = {http://arxiv.org/pdf/1001.2267},
	Volume = {6},
	Abstract = {This paper presents a brief survey on Automatic Speech Recognition and discusses the major themes and advances made in the past 60 years of research, so as to provide a technological perspective and an appreciation of the fundamental progress that has been accomplished in this important area of speech communication. After years of research and development the accuracy of automatic speech recognition remains one of the important research challenges (e.g., variations of the context, speakers, and environment).The design of Speech Recognition system requires careful attentions to the following issues: Definition of various types of speech classes, speech representation, feature extraction techniques, speech classifiers, database and performance evaluation. The problems that are existing in ASR and the various techniques to solve these problems constructed by various research workers have been presented in a chronological order. Hence authors hope that this work shall be a contribution in the area of speech recognition. The objective of this review paper is to summarize and compare some of the well known methods used in various stages of speech recognition system and identify research topic and applications which are at the forefront of this exciting and challenging field.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://arxiv.org/pdf/1001.2267}}

@incollection{garcia_identivox_2000,
	Address = {Madrid},
	Author = {García, M and Ledesma, O and Martínez, E and Ortega, Javier and González Rodríguez, Joaquín},
	Booktitle = {SEAF 2000. Actas del I Congreso de la Sociedad Española de Acústica Forense},
	Date = {2000},
	Date-Modified = {2016-09-24 18:56:04 +0000},
	Keywords = {phonetics, speaker recognition, speech technology},
	Pages = {149-154},
	Publisher = {Escuela Universitaria de Ingenieros Técnicos de Telecomunicación - Sociedad Española de Acústica Forense},
	Title = {IdentiVox 2000: Una herramienta bajo Windows para reconocimiento automático de locutores independiente de texto en aplicaciones forenses}}

@article{dalessandro_synthese_2002,
	Date = {2002},
	Date-Modified = {2016-09-22 20:24:45 +0000},
	Editor = {D'Alessandro, C and Tzoukermann, E},
	Journal = {Traitement automatique des langues},
	Keywords = {compilation, speech synthesis, speech technology},
	Number = {1},
	Title = {Synthèse de la parole à partir du texte},
	Volume = {14},
	Abstract = {Prétraitement et analyse linguistique dans le système de synthèse TTS CVOX. Application à la vocalisation automatique d'e-mails --Nicolas Torzec et al.. LIA\_PHON : un système complet de phonétisation de textes -- Frédéric Béche. Syntaix : une approche métrique-autosegmentale de la prosodies --Albert Di Cristo, Philippe Di Cristo. Une grammaire en tronçons appliquée à la génération de la prosodies -- Philippe Boula de Mareüil et al.. La synthèse de l'intonation à partir de structures syntaxiques riches -- Piet Mertens et al.. Kali : synthèse vocale à partir du texte. De la conception à la mise en ø euvre -- Michel Morel et Anne Lacheret-Dujour. ELAN Text-To-Speech. Un système multilingue de synthèse de la parole à partir du texte -- Philippe Boula de Mareüil et al.. La synthèse du français parlé : le système des laboratoires Bells -- Evelyne Tzoukermann. Le projet EULER. Vers une synthèse de parole générique et multilingues -- Michel Bagein et al.. Cédérom : 33 ans de synthèse de la parole à partir du texte. Une promenade sonore (1968-2001) Christophe d'Alessandro.}}

@incollection{goronzy_other_2006,
	Address = {Burlington, MA},
	Author = {Goronzy, Silke and Tomokiyo, Laura Mayfield and Barnard, Etienne and Davel, Marelie},
	Booktitle = {Multilingual speech processing},
	Date = {2006},
	Date-Modified = {2016-09-24 18:56:04 +0000},
	Editor = {Schultz, Tanja and Kirchhoff, Katrin},
	File = {Attachment:files/4623/Goronzy et al. - 2006 - Other challenges Non-native speech, dialects, accents, and local interfaces.pdf:application/pdf},
	Keywords = {general, L2, multilingualism, speech technology},
	Pages = {273-316},
	Publisher = {Elsevier Academic Press},
	Title = {Other challenges: Non-native speech, dialects, accents, and local interfaces},
	Bdsk-File-1 = {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}}

Paper  bibtex   

@article{puigvi_parametrizacion_1994,
	Author = {Puigví, David and Jiménez, David and Fernández, Josep Maria},
	Date = {1994},
	Date-Modified = {2016-09-23 19:24:11 +0000},
	Journal = {Procesamiento del Lenguaje Natural},
	Keywords = {disfluencies, ESTIVOZ, pause location, pauses, phonetics, prosody, silent pauses, Spanish, speech synthesis, speech technology, temporal factors, text-to-speech},
	Language = {es},
	Title = {Parametrización de las pausas ortográficas en castellano. Aplicación a un conversor de texto en habla},
	Url = {http://liceu.uab.cat/publicacions/Puigvi_Jimenez_Fernandez_94_Pausas_Sintesis_Castellano.pdf http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/3932/2330},
	Volume = {15},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://liceu.uab.cat/publicacions/Puigvi_Jimenez_Fernandez_94_Pausas_Sintesis_Castellano.pdf%20http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/3932/2330}}