Um, one large pizza. A preliminary study of disfluency modelling for improving ASR. Hutchinson, B. & Pereira, C. In DiSS 2001. Proceedings of the ISCA Tutorial and Research Workshop Disfluency in Spontaneous Speech, pages 77–80, 2001. Paper abstract bibtex A corpus of spontaneous telephone transactions between call centre operators of a pizza company and its customers is examined for disfluencies (fillers and speech repairs) with the aim of improving automatic speech recognition. From this, a subset of the customer orders is selected as a test set. An architecture is presented which allows filled pauses and repairs to be detected and corrected. A language repair module removes fillers and reparanda and transforms utterances containing them into fluent utterances. An experiment on filled pauses using this module and architecture is then described. A speech recognition grammar for recognising fluent speech is used to provide a baseline. This grammar is then enriched with filled pauses, based on their placement in relation to syntactic boundaries. Evaluation is done at the level of understanding, using a metric on feature structures. Initial results indicate that incorporating filled pauses at syntactic boundaries improves the recognition results for spontaneous continuous speech containing disfluencies.
@inproceedings{hutchinson_um_2001,
Author = {Hutchinson, Ben and Pereira, Cécile},
Booktitle = {DiSS 2001. Proceedings of the ISCA Tutorial and Research Workshop Disfluency in Spontaneous Speech},
Date = {2001},
Date-Modified = {2018-05-14 08:03:37 +0000},
Eventdate = {2001-08-29/2001-08-31},
Keywords = {conversation, disfluencies, filled pauses, pauses, phonetics, prosody, repairs, speaking styles, speech recognition, speech technology, spontaneous speech, temporal factors},
Location = {Edinburgh, Scotland, UK},
Pages = {77--80},
Title = {Um, one large pizza. A preliminary study of disfluency modelling for improving ASR},
Url = {http://www.isca-speech.org/archive_open/diss_01/dis1_077.html},
Year = {2001},
Abstract = {A corpus of spontaneous telephone transactions between call centre operators of a pizza company and its customers is examined for disfluencies (fillers and speech repairs) with the aim of improving automatic speech recognition. From this, a subset of the customer orders is selected as a test set. An architecture is presented which allows filled pauses and repairs to be detected and corrected. A language repair module removes fillers and reparanda and transforms utterances containing them into fluent utterances. An experiment on filled pauses using this module and architecture is then described. A speech recognition grammar for recognising fluent speech is used to provide a baseline. This grammar is then enriched with filled pauses, based on their placement in relation to syntactic boundaries. Evaluation is done at the level of understanding, using a metric on feature structures. Initial results indicate that incorporating filled pauses at syntactic boundaries improves the recognition results for spontaneous continuous speech containing disfluencies.},
Bdsk-File-1 = {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},
Bdsk-Url-1 = {http://www.isca-speech.org/archive_open/diss_01/dis1_077.html}}
Downloads: 0
{"_id":"FJBKLWF4X3Ecv3j77","bibbaseid":"hutchinson-pereira-umonelargepizzaapreliminarystudyofdisfluencymodellingforimprovingasr-2001","downloads":0,"creationDate":"2016-09-21T09:08:38.059Z","title":"Um, one large pizza. A preliminary study of disfluency modelling for improving ASR","author_short":["Hutchinson, B.","Pereira, C."],"year":2001,"bibtype":"inproceedings","biburl":"https://joaquimllisterri.cat/phonetics/ESTIVOZ/ESTIVOZ.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Hutchinson"],"firstnames":["Ben"],"suffixes":[]},{"propositions":[],"lastnames":["Pereira"],"firstnames":["Cécile"],"suffixes":[]}],"booktitle":"DiSS 2001. Proceedings of the ISCA Tutorial and Research Workshop Disfluency in Spontaneous Speech","date":"2001","date-modified":"2018-05-14 08:03:37 +0000","eventdate":"2001-08-29/2001-08-31","keywords":"conversation, disfluencies, filled pauses, pauses, phonetics, prosody, repairs, speaking styles, speech recognition, speech technology, spontaneous speech, temporal factors","location":"Edinburgh, Scotland, UK","pages":"77–80","title":"Um, one large pizza. A preliminary study of disfluency modelling for improving ASR","url":"http://www.isca-speech.org/archive_open/diss_01/dis1_077.html","year":"2001","abstract":"A corpus of spontaneous telephone transactions between call centre operators of a pizza company and its customers is examined for disfluencies (fillers and speech repairs) with the aim of improving automatic speech recognition. From this, a subset of the customer orders is selected as a test set. An architecture is presented which allows filled pauses and repairs to be detected and corrected. A language repair module removes fillers and reparanda and transforms utterances containing them into fluent utterances. An experiment on filled pauses using this module and architecture is then described. A speech recognition grammar for recognising fluent speech is used to provide a baseline. This grammar is then enriched with filled pauses, based on their placement in relation to syntactic boundaries. Evaluation is done at the level of understanding, using a metric on feature structures. Initial results indicate that incorporating filled pauses at syntactic boundaries improves the recognition results for spontaneous continuous speech containing disfluencies.","bdsk-file-1":"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","bdsk-url-1":"http://www.isca-speech.org/archive_open/diss_01/dis1_077.html","bibtex":"@inproceedings{hutchinson_um_2001,\n\tAuthor = {Hutchinson, Ben and Pereira, Cécile},\n\tBooktitle = {DiSS 2001. Proceedings of the ISCA Tutorial and Research Workshop Disfluency in Spontaneous Speech},\n\tDate = {2001},\n\tDate-Modified = {2018-05-14 08:03:37 +0000},\n\tEventdate = {2001-08-29/2001-08-31},\n\tKeywords = {conversation, disfluencies, filled pauses, pauses, phonetics, prosody, repairs, speaking styles, speech recognition, speech technology, spontaneous speech, temporal factors},\n\tLocation = {Edinburgh, Scotland, UK},\n\tPages = {77--80},\n\tTitle = {Um, one large pizza. A preliminary study of disfluency modelling for improving ASR},\n\tUrl = {http://www.isca-speech.org/archive_open/diss_01/dis1_077.html},\n\tYear = {2001},\n\tAbstract = {A corpus of spontaneous telephone transactions between call centre operators of a pizza company and its customers is examined for disfluencies (fillers and speech repairs) with the aim of improving automatic speech recognition. From this, a subset of the customer orders is selected as a test set. An architecture is presented which allows filled pauses and repairs to be detected and corrected. A language repair module removes fillers and reparanda and transforms utterances containing them into fluent utterances. An experiment on filled pauses using this module and architecture is then described. A speech recognition grammar for recognising fluent speech is used to provide a baseline. This grammar is then enriched with filled pauses, based on their placement in relation to syntactic boundaries. Evaluation is done at the level of understanding, using a metric on feature structures. Initial results indicate that incorporating filled pauses at syntactic boundaries improves the recognition results for spontaneous continuous speech containing disfluencies.},\n\tBdsk-File-1 = {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},\n\tBdsk-Url-1 = {http://www.isca-speech.org/archive_open/diss_01/dis1_077.html}}\n\n","author_short":["Hutchinson, B.","Pereira, C."],"key":"hutchinson_um_2001","id":"hutchinson_um_2001","bibbaseid":"hutchinson-pereira-umonelargepizzaapreliminarystudyofdisfluencymodellingforimprovingasr-2001","role":"author","urls":{"Paper":"http://www.isca-speech.org/archive_open/diss_01/dis1_077.html"},"keyword":["conversation","disfluencies","filled pauses","pauses","phonetics","prosody","repairs","speaking styles","speech recognition","speech technology","spontaneous speech","temporal factors"],"metadata":{"authorlinks":{}},"html":""},"search_terms":["one","large","pizza","preliminary","study","disfluency","modelling","improving","asr","hutchinson","pereira"],"keywords":["conversation","disfluencies","filled pauses","pauses","phonetics","prosody","repairs","speaking styles","speech recognition","speech technology","spontaneous speech","temporal factors"],"authorIDs":[],"dataSources":["qBn3jEfYwFvzHJsYh","BrMmNtBqG9aDvpsZn"]}