{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T14:40:18Z","timestamp":1657377618891},"reference-count":41,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2016]]},"DOI":"10.1587\/transinf.2016slp0020","type":"journal-article","created":{"date-parts":[[2016,9,30]],"date-time":"2016-09-30T22:23:32Z","timestamp":1475274212000},"page":"2490-2498","source":"Crossref","is-referenced-by-count":3,"title":["A Statistical Sample-Based Approach to GMM-Based Voice Conversion Using Tied-Covariance Acoustic Models"],"prefix":"10.1587","volume":"E99.D","author":[{"given":"Shinnosuke","family":"TAKAMICHI","sequence":"first","affiliation":[{"name":"Graduate School of Information Science, Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"TODA","sequence":"additional","affiliation":[{"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] K. Tanaka, T. Toda, G. Neubig, S. Sakti, and S. Nakamura, \u201cA hybrid approach to electrolaryngeal speech enhancement based on noise reduction and statistical excitation generation,\u201d IEICE Trans. Inf. & Syst., vol.E97-D, no.6, pp.1429-1437, June 2014.","DOI":"10.1587\/transinf.E97.D.1429"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] K. Kobayashi, T. Toda, H. Doi, T. Nakano, M. Goto, G. Neubig, S. Sakti, and S. Nakamura, \u201cVoice timbre control based on perceived age in singing voice conversion,\u201d IEICE Trans. Inf. & Syst., vol.E97-D, no.6, pp.1419-1428, June 2014.","DOI":"10.1587\/transinf.E97.D.1419"},{"key":"3","unstructured":"[3] 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 in Proc. INTERSPEECH, pp.2769-2772, Florence, Italy, Aug. 2011."},{"key":"4","unstructured":"[4] S. Aryal and R.G.-Osuna, \u201cCan voice conversion be used to reduce non-native accents?,\u201d in Proc. ICASSP, pp.7929-7933,Florence, Italy, May 2014."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] T. Nakashika, R. Takashima, T. Takiguchi, and Y. Ariki, \u201cVoice conversion in high-order Eigen space using deep belief nets,\u201d in Proc. INTERSPEECH, pp.369-372, Lyon, France, Aug. 2013.","DOI":"10.21437\/Interspeech.2013-102"},{"key":"6","unstructured":"[6] Z. Wu, T. Virtanen, T. Kinnunen, E.S. Chng, and H. Li, \u201cExemplar-based voice conversion using non-negative spectrogram deconvolution,\u201d in Proc. SSW8, pp.201-206, Catalunya, Spain, Aug. 2013."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] E. Helander, H. Sil\u00e9n, T. Virtanen, and M. Gabbouj, \u201cVoice conversion using dynamic kernel partial least squares regression,\u201d IEEE Trans. Audio, Speech, Language Process., vol.20, no.3, pp.806-817, March 2012.","DOI":"10.1109\/TASL.2011.2165944"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Y. Stylianou, O. Capp\u00e9, and E. Moulines, \u201cContinuous probabilistic transform for voice conversion,\u201d IEEE Trans. Speech and Audio Processing, vol.6, no.2, pp.131-142, March 1988.","DOI":"10.1109\/89.661472"},{"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. Audio, Speech, Language Process., vol.15, no.8, pp.2222-2235, 2007.","DOI":"10.1109\/TASL.2007.907344"},{"key":"10","unstructured":"[10] K. Ohta, T. Toda, Y. Ohtani, H. Saruwatari, and K. Shikano, \u201cAdaptive voice-quality control based on one-to-many Eigenvoice conversion,\u201d in Proc. INTERSPEECH, pp.2158-2161, Chiba, Japan, Sept. 2010."},{"key":"11","unstructured":"[11] L.-H. Chen, Z.-H. Ling, Y. Song, and L.-R. Dai, \u201cJoint spectral distribution modeling using restricted Boltzmann machines for voice conversion,\u201d in Proc. INTERSPEECH, pp.3052-3056, Lyon, France, Sept. 2013."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] Z. Wu, P. Swietojanski, C. Veaux, S. Renals, and S. King, \u201cA study of speaker adaptation for DNN-based speech synthesis,\u201d in Proc.INTERSPEECH, pp.879-883, Dresden, Germany, Sept. 2015.","DOI":"10.21437\/Interspeech.2015-270"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] E. Variani, E. McDermott, and G. Heigold, \u201cA Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture,\u201d in Proc. ICASSP, pp.4270-4274, Brisbane, Australia, April 2015.","DOI":"10.1109\/ICASSP.2015.7178776"},{"key":"14","unstructured":"[14] K. Kobayashi, T. Toda, G. Neubig, S. Sakti, and S. Nakamura, \u201cStatistical singing voice conversion with direct waveform modification based on the spectrum differential,\u201d in Proc. INTERSPEECH, pp.2514-2518, Max Atria, Singapore, Sept. 2014."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] 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":"16","doi-asserted-by":"crossref","unstructured":"[16] S. Takamichi, T. Toda, A.W. Black, and S. Nakamura, \u201cModulation spectrum-constrained trajectory training algorithm for GMM-based voice conversion,\u201d in Proc. ICASSP, pp.4859-4863, Brisbane, Australia, April 2015.","DOI":"10.1109\/ICASSP.2015.7178894"},{"key":"17","unstructured":"[17] N. Iwahashi, N. Kaiki, and Y. Sagisaka, \u201cSpeech segment selection for concatenative synthesis based on spectral distortion minimization,\u201d IEICE Trans. Fundamentals, vol.E76-A, no.11, pp.1942-1948, Nov. 1993."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] A.J. Hunt and A.W. Black, \u201cUnit selection in a concatenative speech synthesis system using a large speech database,\u201d in Proc. ICASSP, pp.373-376, Atlanta, U.S.A., May 1996.","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] 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, 2013.","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"20","unstructured":"[20] Z. Ling, L. Qin, H. Lu, Y. Gao, L. Dai, R. Wang, Y. Jiang, Z. Zhao, J. Yang, J. Chen, and G. Hu, \u201cThe USTC and iflytek speech synthesis systems for blizzard challenge 2007,\u201d in Proc. Blizzard Challenge Workshop, pp.1-6, Bonn, Germany, Aug. 2007."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] 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":"22","unstructured":"[22] Z. Yan, Q. Yao, and S.K. Frank, \u201cRich context modeling for high quality HMM-based TTS,\u201d in Proc. INTERSPEECH, pp.1755-1758, Brighton, U.K., Sept. 2009."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, \u201cSpeech parameter generation algorithms for HMM-based speech synthesis,\u201d in Proc. ICASSP, pp.1315-1318, Istanbul, Turkey, June 2000.","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"24","unstructured":"[24] H.-T. Hwang, Y. Tsao, H.-M. Wang, Y.-R. Wang, and S.-H. Chen, \u201cAlleviating the over-smoothing problem in GMM-based voice conversion with discriminative training,\u201d in Proc. INTERSPEECH, pp.3062-3066, Lyon, France, Sept. 2013."},{"key":"25","unstructured":"[25] T. Merritt, J. Yamagishi, Z. Wu, O. Watts, and S. King, \u201cDeep neural network context embeddings for model selection in rich-context HMM synthesis,\u201d in Proc. INTERSPEECH, pp.2207-2211,Dresden, Germany, Sept. 2015."},{"key":"26","unstructured":"[26] K. Shinoda and T. Watanabe, \u201cMDL-based context-dependent subword modeling for speech recognition,\u201d J. Acoust. Soc. Jpn (E), vol.28, no.3, pp.140-146, 2007."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Y. Linde, A. Buzo, and R.M. Gray, \u201cAn algorithm for vector quantizer design,\u201d IEEE Trans. Commun., vol.28, pp.84-95, 1980.","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] T. Dutoit, A. Holzapfel, M. Jottrand, A. Moinet, J. Perez, and Y. Stylianou, \u201cTowards a voice conversion system based on frame selection,\u201d in Proc. ICASSP, pp.513-516, Hawaii, U.S.A., April 2007.","DOI":"10.1109\/ICASSP.2007.366962"},{"key":"29","unstructured":"[29] S. Kataoka, N. Mizutani, K. Tokuda, and T. Kitamura, \u201cDecision tree backing-off in HMM-based speech synthesis,\u201d in Proc.INTERSPEECH, vol.2, pp.1205-1208, Jeju, Korea, Oct. 2004."},{"key":"30","unstructured":"[30] Z. Ling and R. Wang, \u201cHMM-based unit selection using frame sized speech segments,\u201d in Proc. INTERSPEECH, pp.2034-2037, Pittsburgh U.S.A., Sept. 2006."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] T. Koriyama, T. Nose, and T. Kobayashi, \u201cStatistical parametric speech synthesis based on Gaussian process regression,\u201d IEEE J. Sel. Topics Signal Process., vol.8, no.2, pp.173-183, April 2014.","DOI":"10.1109\/JSTSP.2013.2283461"},{"key":"32","unstructured":"[32] N.C.V. Pilkington, H. Zen, and M.J.F. Gales, \u201cGaussian process experts for voice conversion,\u201d in Proc. INTERSPEECH, pp.2761-2764, Florence, Italy, July 2011."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] R. Aihara, T. Takiguchi, and Y. Ariki, \u201cActivity-mapping non-negative matrix factorization for exemplar-based voice conversion,\u201d in Proc. ICASSP, pp.4899-4903, Brisbane, Australia, April 2015.","DOI":"10.1109\/ICASSP.2015.7178902"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] Z. Wu, E.S. Chng, and H. Li, \u201cExemplar-based voice conversion using joint nonnegative matrix factorization,\u201d Multimedia Tools and Applications, vol.74, no.22, pp.9943-9958, 2015.","DOI":"10.1007\/s11042-014-2180-2"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] T. Toda, H. Kawai, M. Tsuzaki, and K. Shikano, \u201cAn evaluation of cost functions sensitively capturing local degradation of naturalness for segment selection in concatenative speech synthesis,\u201d Speech Commun., vol.48, no.1, pp.45-56, 2006.","DOI":"10.1016\/j.specom.2005.05.011"},{"key":"36","unstructured":"[36] Y. Sagisaka, K. Takeda, M. Abe, S. Katagiri, T. Umeda, and H. Kuawhara, \u201cA large-scale Japanese speech database,\u201d in ICSLP90, pp.1089-1092, Kobe, Japan, Nov. 1990."},{"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 2001, pp.1-6, Firentze, Italy, Sept. 2001."},{"key":"38","unstructured":"[38] Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, \u201cMaximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation,\u201d in Proc. INTERSPEECH, pp.2266-2269, Pittsburgh, U.S.A., Sept. 2006."},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] H. Kawahara, I. Masuda-Katsuse, and A.D. Cheveigne, \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, 1999.","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] S. Takamichi, T. Toda, A.W. Black, and S. Nakamura, \u201cParameter generation algorithm considering modulation spectrum for HMM-based speech synthesis,\u201d in Proc. ICASSP, pp.4210-4214, Brisbane, Australia, April 2015.","DOI":"10.1109\/ICASSP.2015.7178764"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] H. Hwang, Y. Tsao, H. Wang, Y. Wang, and S. Chen, \u201cIncorporating global variance in the training phase of GMM-based voice conversion,\u201d in Proc. APSIPA, pp.1-6, Kaohsiung, Taiwan, Oct. 2013.","DOI":"10.1109\/APSIPA.2013.6694179"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/10\/E99.D_2016SLP0020\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T13:59:01Z","timestamp":1657375141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/10\/E99.D_2016SLP0020\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":41,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2016]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2016slp0020","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}