{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T21:18:13Z","timestamp":1783718293575,"version":"3.55.0"},"publisher-location":"Boston","reference-count":19,"publisher":"Kluwer Academic Publishers","isbn-type":[{"value":"1402080018","type":"print"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/0-387-22794-6_11","type":"book-chapter","created":{"date-parts":[[2006,1,10]],"date-time":"2006-01-10T08:08:16Z","timestamp":1136880496000},"page":"167-180","source":"Crossref","is-referenced-by-count":36,"title":["Underlying Principles of a High-quality Speech Manipulation System STRAIGHT and Its Application to Speech Segregation"],"prefix":"10.1007","author":[{"given":"Hideki","family":"Kawahara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshio","family":"Irino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"9","key":"11_CR1","first-page":"1188","volume":"E78-D","author":"T. Abe","year":"1995","unstructured":"Abe, T., Kobayashi, T., and Imai, S., 1995, Harmonics estimation based on instantaneous frequency and its application to pitch determination, IEICE Trans. Information and Systems, E78-D(9): 1188\u20131194.","journal-title":"IEICE Trans. Information and Systems"},{"key":"11_CR2","first-page":"1265","volume":"1","author":"M. Bulut","year":"2002","unstructured":"Bulut, M., Narayanan, S.S., and Syrdal, A.K., 2002, Expressive speech synthesis using a concatenative synthesizer, Proc. ICSLP\u201902, Denver, 1:1265\u20131268.","journal-title":"Proc. ICSLP\u201902, Denver"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Charpentier, F.J., 1986, Pitch detection using the short-term phase spectrum, Proc. ICASSP\u201986, pp. 113\u2013116.","DOI":"10.1109\/ICASSP.1986.1169123"},{"key":"11_CR4","volume-title":"Modeling Auditory Processing and Organization","author":"M. Cooke","year":"1993","unstructured":"Cooke, M., 1993, Modeling Auditory Processing and Organization, Cambridge University Press, Cambridge, UK."},{"key":"11_CR5","first-page":"347","volume-title":"Vocal Fold Physiology: Voice Production, Mechanisms and Functions","author":"H. Fujisaki","year":"1998","unstructured":"Fujisaki, H., 1998, A note on the physiological and physical basis for the phrase and accent components in the voice fundamental frequency contour, in: Vocal Fold Physiology: Voice Production, Mechanisms and Functions, O. Fujimura, ed., Raven Press, New York, pp. 347\u2013355."},{"issue":"3\u20134","key":"11_CR6","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0167-6393(00)00085-6","volume":"36","author":"T. Irino","year":"2002","unstructured":"Irino, T. and Patterson, R.D., 2002, Segregating information about the size and shape of the vocal tract using a time-domain auditory model: The stabilized wavelet Mellin transform, Speech Communication, 36(3\u20134):181\u2013203.","journal-title":"Speech Communication"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Irino, T., Patterson, R.D., and Kawahara, H., 2003, Speech segregation based on fundamental event information using an auditory vocoder, Proc. Eurospeech\u201903, Geneva, pp. 553\u2013556.","DOI":"10.21437\/Eurospeech.2003-224"},{"issue":"3\u20134","key":"11_CR8","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H. Kawahara","year":"1999","unstructured":"Kawahara, H., Masuda-Katsuse, I., and de Cheveign\u00e9, A., 1999a, Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction, Speech Communication, 27(3\u20134):187\u2013207.","journal-title":"Speech Communication"},{"key":"11_CR9","first-page":"2781","volume":"6","author":"H. Kawahara","year":"1999","unstructured":"Kawahara, H., Katayose, H., de Cheveign\u00e9, A., and Patterson, R.D., 1999b, Fixed-point analysis of frequency to instantaneous frequency mapping for accurate estimation of F0 and periodicity, Proc. Eurospeech\u201999, 6:2781\u20132784.","journal-title":"Proc. Eurospeech\u201999"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Atake, Y., and Zolfaghari, P., 2000, Accurate vocal event detection method based on a fixed-point analysis of mapping from time to weighted average group delay, Proc. ICSLP\u20192000, pp. 664\u2013667.","DOI":"10.21437\/ICSLP.2000-899"},{"key":"11_CR11","unstructured":"Kawahara, H., Estill, J., and Fujimura, O., 2001a, Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT, Proc. 2nd MAVEBA, [CD ROM]."},{"key":"11_CR12","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.1121\/1.4744588","volume":"109","author":"H. Kawahara","year":"2001","unstructured":"Kawahara, H. and Katayose, H., 2001b, Scat singing generation using a versatile speech manipulation system, STRAIGHT, 141st meeting of the Acoust. Soc. Amer., Chicago, 109:2425\u20132426.","journal-title":"141st meeting of the Acoust. Soc. Amer., Chicago"},{"issue":"2","key":"11_CR13","first-page":"208","volume":"43","author":"H. Kawahara","year":"2002","unstructured":"Kawahara, H. and Katayose, H., 2002a, Scat generation research program based on STRAIGHT, a high-quality speech analysis, modification and synthesis system, J. of IPSJ, 43(2):208\u2013218, [in Japanese].","journal-title":"J. of IPSJ"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Kawahara, H., 2002b, Systematic downgrading for investigating \u201cnaturalness\u201d in synthesized singing using STRAIGHT: A high quality VOCODER, 143rd meeting of the Acoust. Soc. Amer., Pittsburgh, p. 2334.","DOI":"10.1121\/1.4777797"},{"key":"11_CR15","first-page":"256","volume":"1","author":"H. Kawahara","year":"2003","unstructured":"Kawahara, H. and Matsui, H., 2003, Auditory morphing based on an elastic perceptual distance metric in an interference-free time-frequency representation, Proc. ICASSP\u20192003, 1:256\u2013259.","journal-title":"Proc. ICASSP\u20192003"},{"key":"11_CR16","unstructured":"Kawahara, H., 2003b, Exemplar-based voice quality analysis and control using a high quality auditory morphing procedure based on STRAIGHT, Proc. VOQUAL\u201903, Geneva, pp. 109\u2013114"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Banno, H., Irino, T., and Zolfaghari, P., 2004, Algorithm amalgam: morphing waveform based methods, sinusoidal models and STRAIGHT, Proc. ICASSP\u201904 [accepted for publication].","DOI":"10.1109\/ICASSP.2004.1325910"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Matsui, H. and Kawahara, H., 2003, Investigation of emotionally morphed speech perception and its structure using a high quality speech manipulation system, Proc. Eurospeech\u201903, Geneva, pp.2113\u20132116.","DOI":"10.21437\/Eurospeech.2003-610"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1121\/1.414456","volume":"98","author":"R.D. Patterson","year":"1995","unstructured":"Patterson, R.D., Allerhand, M., and Giguere, C., 1995, Time-domain modeling of peripheral auditory processing: a modular architecture and a software platform, J. Acoust. Soc. Amer., 98:1890\u20131894.","journal-title":"J. Acoust. Soc. Amer."}],"container-title":["Speech Separation by Humans and Machines"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/0-387-22794-6_11.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T04:24:22Z","timestamp":1683347062000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/0-387-22794-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["1402080018"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/0-387-22794-6_11","relation":{},"subject":[]}}