{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:19:07Z","timestamp":1742915947458,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540731085"},{"type":"electronic","value":"9783540731108"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-73110-8_5","type":"book-chapter","created":{"date-parts":[[2007,8,23]],"date-time":"2007-08-23T10:33:29Z","timestamp":1187865209000},"page":"40-49","source":"Crossref","is-referenced-by-count":0,"title":["Enrich Web Applications with Voice Internet Persona Text-to-Speech for Anyone, Anywhere"],"prefix":"10.1007","author":[{"given":"Min","family":"Chu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Soong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Wang, W.J., Campbell, W.N., Iwahashi, N., Sagisaka, Y.: Tree-Based Unit Selection for English Speech Synthesis. In: Proc. of ICASSP-1993, Minneapolis, vol.2, pp. 191\u2013194 (1993)","DOI":"10.1109\/ICASSP.1993.319266"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Hunt, A.J., Black, A.W.: Unit Selection in a Concatentive Speech Synthesis System Using a Large Speech Database. In: Proc. of ICASSP- 1996, Atlanta, vol. 1, pp. 373\u2013376 (1996)","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chu, M., Peng, H., Yang, H.Y., Chang, E.: Selecting Non-Uniform Units from a Very Large Corpus for Concatenative Speech Synthesizer. In: Proc. of ICASSP-2001, Salt Lake City, vol. 2, pp. 785\u2013788 (2001)","DOI":"10.1109\/ICASSP.2001.941032"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Yoshimura, T., Tokuda, K., Masuku, T., Kobayashi, T., Kitamura, T.: Simultaneous Modeling Spectrum, Pitch and Duration in HMM-based Speech Synthesis. In: Proc. of European Conference on Speech Communication and Technology, Budapest, vol. 5, pp. 2347\u20132350","DOI":"10.21437\/Eurospeech.1999-596"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Tokuda, K., Kobayashi, T., Masuko, T., Kobayashi, T., Kitamura, T.: Speech Parameter Generation Algorithms for HMM-based Speech Synthesis. In: Proc. of ICASSP-2000, Istanbul, vol. 3, pp. 1315\u20131318 (2000)","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"5_CR6","unstructured":"Tokuda, K., Zen, H., Black, A.W.: An HMM-based Speech Synthesis System Applied to English. In: Proc. of 2002 IEEE Speech Synthesis Workshop, Santa Monica, pp. 11\u201313 (2002)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Chu, M., Peng, H., Zhao, Y., Niu, Z., Chang, E.: Microsoft Mulan \u2014 a bilingual TTS systems. In: Proc. of ICASSP-2003, Hong Kong, vol. 1, pp. 264-267 (2003)","DOI":"10.1109\/ICASSP.2003.1198768"},{"key":"5_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/11939993_26","volume-title":"Chinese Spoken Language Processing","author":"Y. Qian","year":"2006","unstructured":"Qian, Y., Soong, F., Chen, Y.N., Chu, M.: An HMM-Based Mandarin Chinese Text-to-Speech System. In: Huo, Q., Ma, B., Chng, E.-S., Li, H. (eds.) ISCSLP 2006. LNCS (LNAI), vol.\u00a04274, pp. 223\u2013232. Springer, Heidelberg (2006)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Black, A.W., Taylor, P.: Automatic Clustering Similar Units for Unit Selection in Speech Synthesis. In: Proc. of Eurospeech-1997, Rhodes, vol. 2, pp. 601\u2013604 (1997)","DOI":"10.21437\/Eurospeech.1997-219"},{"issue":"6","key":"5_CR10","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1016\/j.specom.2005.10.003","volume":"48","author":"M. Chu","year":"2006","unstructured":"Chu, M., Zhao, Y., Chang, E.: Modeling Stylized Invariance and Local Variability of Prosody in Text-to-Speech Synthesis. Speech Communication\u00a048(6), 716\u2013726 (2006)","journal-title":"Speech Communication"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Chu, M., Peng, H.: An Objective Measure for Estimating MOS of Synthesized Speech. In: Proc. of Eurospeech-2001, Aalborg, pp. 2087\u20132090 (2001)","DOI":"10.21437\/Eurospeech.2001-492"},{"key":"5_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/11939993_74","volume-title":"Chinese Spoken Language Processing","author":"M. Chu","year":"2006","unstructured":"Chu, M., Zhao, Y., Chen, Y.N., Wang, L.J., Soong, F.: The Paradigm for Creating Multi-Lingual Text-to-Speech Voice Database. In: Huo, Q., Ma, B., Chng, E.-S., Li, H. (eds.) ISCSLP 2006. LNCS (LNAI), vol.\u00a04274, pp. 736\u2013747. Springer, Heidelberg (2006)"},{"issue":"4","key":"5_CR13","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1109\/TASSP.1986.1164910","volume":"34","author":"R.J. McAulay","year":"1986","unstructured":"McAulay, R.J., Quatieri, T.F: Speech Analysis\/Synthesis Based on a Sinusoidal Representation. IEEE Trans. ASSP\u00a034(4), 744\u2013754 (1986)","journal-title":"IEEE Trans. ASSP"}],"container-title":["Lecture Notes in Computer Science","Human-Computer Interaction. HCI Intelligent Multimodal Interaction Environments"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-73110-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T15:42:16Z","timestamp":1737387736000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-73110-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540731085","9783540731108"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-73110-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}