Scat singing generation using a versatile speech manipulation system, STRAIGHT. Kawahara, H. & Katayose, H. The Journal of the Acoustical Society of America, 109(5):2425--2426, May, 2001. Paper doi abstract bibtex A set of procedures to generate scat singing by manipulating a small set of seed voices using a speech manipulation system called STRAIGHT [Kawahara et al., Speech Commun. 27, 187–207 (1999)] is proposed. F0 adaptive spectral smoothing based on a second‐order cardinal spline combined with an F0 extractor based on a fixed‐point analysis from filter center frequencies to the output instantaneous frequency enables the STRAIGHT system to generate a highly natural manipulated singing sound. Group delay manipulation for generating the excitation source signal introduces new control flexibility in source characteristics. F0 trajectories are generated using a dynamical model based on F0 feed‐forward control regulated by auditorily mediated feedback [Kawahara et al., Vocal Fold Physiology , edited by H. Fletcher and P. Davis, pp. 263–278 (1996)]. Effects of the spectral interpolation function and interactions between F0 and the spectral envelope are also discussed and demonstrations of a scat chorus are presented. [Work supported by CREST and MEXT, Japan.]
@article{ kawahara_scat_2001,
title = {Scat singing generation using a versatile speech manipulation system, {STRAIGHT}},
volume = {109},
issn = {0001-4966},
url = {http://scitation.aip.org/content/asa/journal/jasa/109/5/10.1121/1.4744588},
doi = {10.1121/1.4744588},
abstract = {A set of procedures to generate scat singing by manipulating a small set of seed voices using a speech manipulation system called {STRAIGHT} [Kawahara et al., Speech Commun. 27, 187–207 (1999)] is proposed. F0 adaptive spectral smoothing based on a second‐order cardinal spline combined with an F0 extractor based on a fixed‐point analysis from filter center frequencies to the output instantaneous frequency enables the {STRAIGHT} system to generate a highly natural manipulated singing sound. Group delay manipulation for generating the excitation source signal introduces new control flexibility in source characteristics. F0 trajectories are generated using a dynamical model based on F0 feed‐forward control regulated by auditorily mediated feedback [Kawahara et al., Vocal Fold Physiology , edited by H. Fletcher and P. Davis, pp. 263–278 (1996)]. Effects of the spectral interpolation function and interactions between F0 and the spectral envelope are also discussed and demonstrations of a scat chorus are presented. [Work supported by {CREST} and {MEXT}, Japan.]},
number = {5},
urldate = {2014-08-07TZ},
journal = {The Journal of the Acoustical Society of America},
author = {Kawahara, Hideki and Katayose, Haruhiro},
month = {May},
year = {2001},
keywords = {Acoustic analysis, Acoustic spectrum analyzers, Acoustics, Singing, Speech},
pages = {2425--2426}
}
Downloads: 0
{"_id":{"_str":"53e6e293bcacdd3f5400091b"},"__v":0,"authorIDs":[],"author_short":["Kawahara, H.","Katayose, H."],"bibbaseid":"kawahara-katayose-scatsinginggenerationusingaversatilespeechmanipulationsystemstraight-2001","bibdata":{"downloads":0,"keyword":["Acoustic analysis","Acoustic spectrum analyzers","Acoustics","Singing","Speech"],"urls":{"Paper":"http://scitation.aip.org/content/asa/journal/jasa/109/5/10.1121/1.4744588"},"role":"author","bibbaseid":"kawahara-katayose-scatsinginggenerationusingaversatilespeechmanipulationsystemstraight-2001","year":"2001","volume":"109","urldate":"2014-08-07TZ","url":"http://scitation.aip.org/content/asa/journal/jasa/109/5/10.1121/1.4744588","type":"article","title":"Scat singing generation using a versatile speech manipulation system, STRAIGHT","pages":"2425--2426","number":"5","month":"May","keywords":"Acoustic analysis, Acoustic spectrum analyzers, Acoustics, Singing, Speech","key":"kawahara_scat_2001","journal":"The Journal of the Acoustical Society of America","issn":"0001-4966","id":"kawahara_scat_2001","doi":"10.1121/1.4744588","bibtype":"article","bibtex":"@article{ kawahara_scat_2001,\n title = {Scat singing generation using a versatile speech manipulation system, {STRAIGHT}},\n volume = {109},\n issn = {0001-4966},\n url = {http://scitation.aip.org/content/asa/journal/jasa/109/5/10.1121/1.4744588},\n doi = {10.1121/1.4744588},\n abstract = {A set of procedures to generate scat singing by manipulating a small set of seed voices using a speech manipulation system called {STRAIGHT} [Kawahara et al., Speech Commun. 27, 187–207 (1999)] is proposed. F0 adaptive spectral smoothing based on a second‐order cardinal spline combined with an F0 extractor based on a fixed‐point analysis from filter center frequencies to the output instantaneous frequency enables the {STRAIGHT} system to generate a highly natural manipulated singing sound. Group delay manipulation for generating the excitation source signal introduces new control flexibility in source characteristics. F0 trajectories are generated using a dynamical model based on F0 feed‐forward control regulated by auditorily mediated feedback [Kawahara et al., Vocal Fold Physiology , edited by H. Fletcher and P. Davis, pp. 263–278 (1996)]. Effects of the spectral interpolation function and interactions between F0 and the spectral envelope are also discussed and demonstrations of a scat chorus are presented. [Work supported by {CREST} and {MEXT}, Japan.]},\n number = {5},\n urldate = {2014-08-07TZ},\n journal = {The Journal of the Acoustical Society of America},\n author = {Kawahara, Hideki and Katayose, Haruhiro},\n month = {May},\n year = {2001},\n keywords = {Acoustic analysis, Acoustic spectrum analyzers, Acoustics, Singing, Speech},\n pages = {2425--2426}\n}","author_short":["Kawahara, H.","Katayose, H."],"author":["Kawahara, Hideki","Katayose, Haruhiro"],"abstract":"A set of procedures to generate scat singing by manipulating a small set of seed voices using a speech manipulation system called STRAIGHT [Kawahara et al., Speech Commun. 27, 187–207 (1999)] is proposed. F0 adaptive spectral smoothing based on a second‐order cardinal spline combined with an F0 extractor based on a fixed‐point analysis from filter center frequencies to the output instantaneous frequency enables the STRAIGHT system to generate a highly natural manipulated singing sound. Group delay manipulation for generating the excitation source signal introduces new control flexibility in source characteristics. F0 trajectories are generated using a dynamical model based on F0 feed‐forward control regulated by auditorily mediated feedback [Kawahara et al., Vocal Fold Physiology , edited by H. Fletcher and P. Davis, pp. 263–278 (1996)]. Effects of the spectral interpolation function and interactions between F0 and the spectral envelope are also discussed and demonstrations of a scat chorus are presented. [Work supported by CREST and MEXT, Japan.]"},"bibtype":"article","biburl":"http://bibbase.org/zotero/naveda","creationDate":"2014-08-10T03:10:11.288Z","downloads":0,"keywords":["acoustic analysis","acoustic spectrum analyzers","acoustics","singing","speech"],"search_terms":["scat","singing","generation","using","versatile","speech","manipulation","system","straight","kawahara","katayose"],"title":"Scat singing generation using a versatile speech manipulation system, STRAIGHT","year":2001,"dataSources":["jmAAmrBSgK57edvso"]}