{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T22:40:06Z","timestamp":1718923206686},"reference-count":41,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2016]]},"DOI":"10.1587\/transinf.2016edp7231","type":"journal-article","created":{"date-parts":[[2016,11,30]],"date-time":"2016-11-30T22:13:10Z","timestamp":1480543990000},"page":"3132-3139","source":"Crossref","is-referenced-by-count":5,"title":["Non-Native Text-to-Speech Preserving Speaker Individuality Based on Partial Correction of Prosodic and Phonetic Characteristics"],"prefix":"10.1587","volume":"E99.D","author":[{"given":"Yuji","family":"OSHIMA","sequence":"first","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"TAKAMICHI","sequence":"additional","affiliation":[{"name":"Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"TODA","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"},{"name":"Information Technology Center, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Graham","family":"NEUBIG","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"SAKTI","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"NAKAMURA","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] H. Zen and A. Senior, \u201cDeep mixture density networks for acoustic modeling in statistical parametric speech synthesis,\u201d Proc. ICASSP, pp.3872-3876, Florence, Italy, May 2014.","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] S. Takamichi, T. Toda, Y. Shiga, S. Sakti, G. Neubig, and S.Nakamura, \u201cParameter generation methods with rich context models for high-quality and flexible text-to-speech synthesis,\u201d IEEE J. Sel. Topics Signal Process., vol.8, no.2, pp.239-250, 2014.","DOI":"10.1109\/JSTSP.2013.2288599"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] S. Takamichi, T. Toda, A.W. Black, G. Neubig, S. Sakti, and S. Nakamura, \u201cPostfilters to modify the modulation spectrum for statistical parametric speech synthesis,\u201d IEEE Trans. Audio, Speech, Language Process., vol.24, no.4, pp.755-767, 2016.","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] J. Yamagishi, T. Nose, H. Zen, Z.-H. Ling, T. Toda, K. Tokuda, S. King, and S. Renals, \u201cRobust speaker-adaptive HMM-based text-to-speech synthesis,\u201d IEEE Trans. ASLP, vol.17, no.6, pp.1208-1230, June 2009.","DOI":"10.1109\/TASL.2009.2016394"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] P. Lanchantin, M.J.F. Gales, S. King, and J. Yamagishi, \u201cMultiple-average-voice-based speech synthesis,\u201d Proc. ICASSP, pp.285-289, Florence, Italy, May 2014.","DOI":"10.1109\/ICASSP.2014.6853603"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] H. Zen, K. Tokuda, and A.W. Black, \u201cStatistical parametric speech synthesis,\u201d Speech Commun., vol.51, no.11, pp.1039-1064, 2009.","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] A.W. Black, \u201cSpeech synthesis for educational technology,\u201d Proc. SLaTE, pp.104-107, Farmington, PA, USA, Oct. 2007.","DOI":"10.21437\/SLaTE.2007-25"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] J. Dines, H. Liang, L. Saheer, M. Gibson, W. Byrne, K. Oura, K. Tokuda, J. Yamagishi, S. King, M. Wester, T. Hirsim\u00e4ki, R. Karhila, and M. Kurimo, \u201cPersonalising speech-to-speech translation: unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis,\u201d Computer Speech & Language, vol.27, no.2, pp.420-437, Feb. 2013.","DOI":"10.1016\/j.csl.2011.08.003"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] T. Toda, A.W. Black, and K. Tokuda, \u201cVoice conversion based on maximum-likelihood estimation of spectral parameter trajectory,\u201d IEEE Trans. ASLP, vol.15, no.8, pp.2222-2235, Nov. 2007.","DOI":"10.1109\/TASL.2007.907344"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] K. Tokuda, Y. Nankaku, T. Toda, H. Zen, J. Yamagishi, and K. Oura, \u201cSpeech synthesis based on hidden Markov models,\u201d Proc. IEEE, vol.101, no.5, pp.1234-1252, April 2013.","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"11","unstructured":"[11] M. Charlier, Y. Ohtani, T. Toda, A. Moinet, and T. Dutoit, \u201cCross-language voice conversion based on eigenvoices,\u201d Proc.INTERSPEECH, pp.1635-1638, Brighton, UK, Sept. 2009."},{"key":"12","unstructured":"[12] N. Hattori, T. Toda, H. Kawai, H. Saruwatari, and K. Shikano, \u201cSpeaker-adaptive speech synthesis based on eigenvoice conversion and language-dependent prosodic conversion in speech-to-speech translation,\u201d Proc. INTERSPEECH, pp.2769-2772, Aug. 2011."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Qian, H. Liang, and F.K. Soong, \u201cA cross-language state sharing and mapping approach to bilingual (Mandarin-English) TTS,\u201d IEEE Trans. Audio, Speech, Language Process., vol.17, no.6, pp.1231-1239, Aug. 2009.","DOI":"10.1109\/TASL.2009.2015708"},{"key":"14","unstructured":"[14] Y.-J. Wu, Y. Nankaku, and K. Tokuda, \u201cState mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis,\u201d Proc. INTERSPEECH, pp.528-531, Brighton, UK, Sept. 2009."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] K. Oura, J. Yamagishi, M. Wester, S. King, and K. Tokuda, \u201cAnalysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,\u201d Speech Commun., vol.54, no.6, pp.703-714, 2012.","DOI":"10.1016\/j.specom.2011.12.004"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. Qian, J. Xu, and F.K. Soong, \u201cA frame mapping based HMM approach to cross-lingual voice transformation,\u201d Proc. ICASSP, pp.5120-5123, May 2011.","DOI":"10.1109\/ICASSP.2011.5947509"},{"key":"17","unstructured":"[17] S. Kajima, A. Iida, K. Yasu, Y. Aikawa, T. Arai, and T. Sugawara, \u201cDevelopment of a Japanese and English speech synthesis system based on HMM using voice conversion for the people with speech communication disorder,\u201d SIG-SLP (in Japanese), vol.2008, no.12, pp.121-126, Feb. 2008."},{"key":"18","unstructured":"[18] A.C. Janska and R.A. Clark, \u201cNative and non-native speaker judgements on the quality of synthesized speech,\u201d Proc. INTERSPEECH, pp.1121-1124, Makuhari, Japan, Sept. 2010."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] S. Aryal and R. Gutierrez-Osuna, \u201cCan voice conversion be used to reduce non-native accents?,\u201d Proc. ICASSP, pp.7879-7883,Florence, Italy, May 2014.","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"20","unstructured":"[20] N. Minematsu, Y. Tomiyama, K. Yoshimoto, K. Shimizu, S.Nakagawa, M. Dantsuji, and S. Makino, \u201cDevelopment of English speech database read by Japanese to support CALL research,\u201d Proc. ICA, vol.1, pp.557-560, 2004."},{"key":"21","unstructured":"[21] P. Ladefoged, A Course in Phonetics, Third Edition, Harcourt Brace Jovanovich College Publishers, 1993."},{"key":"22","unstructured":"[22] S. Kohmoto, Applied English phonology: teaching of English pronunciation to the native Japanese speaker, Tanaka Press, Tokyo, Japan, 1965."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. Oshima, S. Takamichi, T. Toda, G. Neubig, S. Sakti, and S.Nakamura, \u201cNon-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics,\u201d Proc. INTERSPEECH, pp.299-303, Dresden, Germany, Sept. 2015.","DOI":"10.21437\/Interspeech.2015-121"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] J. Yamagishi, C. Veaux, S. King, and S. Renals, \u201cSpeech synthesis technologies for individuals with vocal disabilities: Voice banking and reconstruction,\u201d Acoust. Sci. technol., vol.33, no.1, pp.1-5, 2012.","DOI":"10.1250\/ast.33.1"},{"key":"25","unstructured":"[25] T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T.Kitamura, \u201cSimultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis,\u201d Proc. EUROSPEECH, pp.2347-2350, Budapest, Hungary, April 1999."},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] J. Yamagishi and T. Kobayashi, \u201cAverage-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training,\u201d IEICE Trans. Inf. & Syst., vol.E90-D, no.2, pp.533-543, Feb. 2007.","DOI":"10.1093\/ietisy\/e90-d.2.533"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T.Kitamura, \u201cSpeech parameter generation algorithms for HMM-based speech synthesis,\u201d Proc. ICASSP, vol.3, pp.1315-1318, June 2000.","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"28","unstructured":"[28] N. Minematsu, C. Guo, and K. Hirose, \u201cCART-based factor analysis of intelligibility reduction in Japanese English,\u201d Proc.INTERSPEECH, pp.2069-2072, Geneva, Switzerland, Sept. 2003."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] H. Suzuki, G. Ohyama, and S. Kiritani, \u201cIn search of a method to improve the prosodic features of English spoken by Japanese,\u201d Proc. ICSLP, pp.965-968, Kobe, Japan, Nov. 1990.","DOI":"10.21437\/ICSLP.1990-254"},{"key":"30","unstructured":"[30] T. Kitamura and M. Akagi, \u201cSpeaker individualities in speech spectral envelopes,\u201d Proc. ICSLP, vol.3, pp.1183-1186, 1994."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] T. Kitamura and M. Akagi, \u201cSpeaker individualities in speech spectral envelopes and fundamental frequency contours,\u201d In Speaker Classification II, pp.157-176, Springer, 2007.","DOI":"10.1007\/978-3-540-74122-0_14"},{"key":"32","unstructured":"[32] D. Erro and A. Moreno, \u201cFrame alignment method for cross-lingual voice conversion,\u201d Proc. INTERSPEECH, pp.1969-1972, Antwerp, Belgium, Aug. 2007."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] D. Sundermann, H. Hoge, A. Bonafonte, H. Ney, A. Black, and S. Narayanan, \u201cText-independent voice conversion based on unit selection,\u201d Proc. ICASSP, pp.81-84, Toulose, France, May 2006.","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"34","unstructured":"[34] J. Kominek and A.W. Black, \u201cCMU ARCTIC databases for speech synthesis CMU Language Technologies Institute,\u201d CMU-LTI-03-177, Tech. Rep., 2003."},{"key":"35","unstructured":"[35] Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, \u201cMaximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation,\u201d Proc. INTERSPEECH, pp.2266-2269, Pittsburgh, PA, USA, Sept. 2006."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] H. Kawahara, I. Masuda-Katsuse, and A. de Cheveign\u00e9, \u201cRestructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds,\u201d Speech Commun., vol.27, no.3-4, pp.187-207, April 1999.","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"37","unstructured":"[37] H. Kawahara, J. Estill, and O. Fujimura, \u201cAperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT,\u201d In MAVEBA, pp.59-64, Sept. 2001."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] H. Zen, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, \u201cA Hidden semi-Markov model-based speech synthesis system,\u201d IEICE Trans. Inf. & Syst., vol.E90-D, no.5, pp.825-834, 2007.","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] J. Yamagishi, T. Kobayashi, Y. Nakano, K. Ogata, and J. Isogai, \u201cAnalysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm,\u201d IEEE Trans. Audio, Speech, Language Process., vol.17, no.1, pp.66-83, 2009.","DOI":"10.1109\/TASL.2008.2006647"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, and D.S.Pallett, \u201cDARPA TIMIT acoustic-phonetic continous speech corpus,\u201d NISTIR 4930, NIST, Gaithersburg, MD, Tech. Rep., 1993.","DOI":"10.6028\/NIST.IR.4930"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] C. Beno\u00eet, M. Grice, and V. Hazan, \u201cThe SUS test: a method for the assessment of text-to-speech synthesis intelligibility using Semantically Unpredictable Sentences,\u201d Speech Communication, vol.18, no.4, pp.381-392, 1996.","DOI":"10.1016\/0167-6393(96)00026-X"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/12\/E99.D_2016EDP7231\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T22:19:00Z","timestamp":1718921940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/12\/E99.D_2016EDP7231\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":41,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2016]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2016edp7231","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}