{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T17:43:24Z","timestamp":1725731004670},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642388460"},{"type":"electronic","value":"9783642388477"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38847-7_12","type":"book-chapter","created":{"date-parts":[[2013,6,10]],"date-time":"2013-06-10T22:38:00Z","timestamp":1370903880000},"page":"89-96","source":"Crossref","is-referenced-by-count":0,"title":["Average Voice Modeling Based on Unbiased Decision Trees"],"prefix":"10.1007","author":[{"given":"Fahimeh","family":"Bahmaninezhad","sequence":"first","affiliation":[]},{"given":"Soheil","family":"Khorram","sequence":"additional","affiliation":[]},{"given":"Hossein","family":"Sameti","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Hidden semi-Markov model based speech synthesis. In: Proc. ICSLP, vol.\u00a02, pp. 1397\u20131400 (October 2004)","DOI":"10.21437\/Interspeech.2004-460"},{"key":"12_CR2","unstructured":"Yamagishi, J., Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T.: A training method of average voice model for HMM-based speech synthesis. IEICE Trans. Fundamentals\u00a0E86-A(8), 1956\u20131963 (2003)"},{"key":"12_CR3","unstructured":"Yamagishi, J.: Average-voice-based speech synthesis. Ph.D. thesis, Tokyo Institute of Technology (2006)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Bahmaninezhad, F., Sameti, H., Khorram, S.: HMM-based persian speech synthesis using limited adaptation data. In: 11th International Conference on Signal Processing (ICSP 2012), October 21-25. IEEE (2012)","DOI":"10.1109\/ICoSP.2012.6491556"},{"key":"12_CR5","unstructured":"Yamagishi, J., Masuko, T., Tokuda, K., Kobayashi, T.: A training method for average voice model based on shared decision tree context clustering and speaker adaptive training. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003), vol.\u00a01, IEEE (April 2003)"},{"key":"12_CR6","unstructured":"Yamagishi, J., Ogata, K., Nakano, Y., Isogai, J., Kobayashi, T.: HSMM-based model adaptation algorithms for average-voice-based speech synthesis. In: Proc. ICASSP, Toulouse, France, vol.\u00a0I, pp. 77\u201380 (May 2006)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Yamagishi, J., Usabaev, B., King, S., Watts, O., Dines, J., Tian, J., Hu, R., Oura, K., Tokuda, K., Karhila, R., Kurimo, M.: Thousands of voices for HMM-based speech synthesis. In: Proc. Interspeech, pp. 420\u2013423 (2009)","DOI":"10.21437\/Interspeech.2009-140"},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1250\/ast.21.79","volume":"21","author":"K. Shinoda","year":"2000","unstructured":"Shinoda, K., Watanabe, T.: MDL-based context-dependent subword modeling for speech recognition. J. Acoust. Soc. Japan (E)\u00a021, 79\u201386 (2000)","journal-title":"J. Acoust. Soc. Japan (E)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Young, S.J., Odell, J.J., Woodland, P.C.: Tree-based state tying for high accuracy acoustic modeling. In: Proc. ARPA Human Language Technology Workshop, pp. 307\u2013312 (March 1994)","DOI":"10.3115\/1075812.1075885"},{"key":"12_CR10","unstructured":"Tokuda, K., Masuko, T., Miyazaki, N., Kobayashi, T.: Multi-Space Probability Distribution HMM. IEICE Transaction on Information and Systems E85-D(3), 455\u2013464 (2002)"},{"issue":"1","key":"12_CR11","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TASL.2008.2006647","volume":"17","author":"J. Yamagishi","year":"2009","unstructured":"Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., Isogai, J.: Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm. IEEE Trans. Audio, Speech, Lang. Process.\u00a017(1), 66\u201383 (2009)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"2","key":"12_CR12","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"C.J. Leggetter","year":"1995","unstructured":"Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language\u00a09(2), 171\u2013185 (1995)","journal-title":"Computer Speech and Language"},{"key":"12_CR13","unstructured":"Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T.: Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR. In: Proc. ICASSP, pp. 805\u2013808 (May 2001)"},{"issue":"4","key":"12_CR14","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1109\/78.80902","volume":"39","author":"C.H. Lee","year":"1992","unstructured":"Lee, C.H., Lin, C.H., Juang, B.H.: A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models. IEEE Trans. Acoust., Speech, Signal Processing\u00a039(4), 806\u2013814 (1992)","journal-title":"IEEE Trans. Acoust., Speech, Signal Processing"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Tsurumi, Y., Nakagawa, S.: An Unsupervised Speaker Adaptation Method for Continuous Parameter HMM by Maximum a Posteriori Probability Estimation. In: Proc. ICSLP 1994, S09-1.1, pp. 431\u2013434 (1994)","DOI":"10.21437\/ICSLP.1994-122"},{"key":"12_CR16","unstructured":"Bijankhan, M., Sheikhzadegan, J., Roohani, M.R., Samareh, Y., Lucas, C., Tebiani, M.: The Speech Database of Farsi Spoken Language. In: Proc. 5th Australian Int. Conf. Speech Science and Technology (SST 1994), pp. 826\u2013831 (1994)"},{"issue":"3-4","key":"12_CR17","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H. Kawahara","year":"1999","unstructured":"Kawahara, H., Masuda-Katsuse, I., de Cheveign, A.: Restructuring Speech Representations Using a Pitch-Adaptive Time-Frequency Smoothing and an Instantaneous-Frequency-based F0 Extraction: Possible Role of a Repetitive Structure in Sounds. Speech Communication\u00a027(3-4), 187\u2013207 (1999)","journal-title":"Speech Communication"},{"key":"12_CR18","unstructured":"Recommendation ITU-U p.800, Methods for subjective determination of transmission quality. In: International Telecommunication Union (August 1996)"}],"container-title":["Lecture Notes in Computer Science","Advances in Nonlinear Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38847-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T05:16:56Z","timestamp":1688275016000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-38847-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642388460","9783642388477"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38847-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}