{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:29:05Z","timestamp":1778048945300,"version":"3.51.4"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319455099","type":"print"},{"value":"9783319455105","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45510-5_38","type":"book-chapter","created":{"date-parts":[[2016,9,2]],"date-time":"2016-09-02T11:03:04Z","timestamp":1472814184000},"page":"335-342","source":"Crossref","is-referenced-by-count":2,"title":["Unit-Selection Speech Synthesis Adjustments for Audiobook-Based Voices"],"prefix":"10.1007","author":[{"given":"Jakub","family":"V\u00edt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jind\u0159ich","family":"Matou\u0161ek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,3]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/978-3-540-49127-9_21","volume-title":"Springer Handbook of Speech Processing","author":"T Dutoit","year":"2008","unstructured":"Dutoit, T.: Corpus-based speech synthesis. In: Benesty, J., Sondhi, M., Huang, Y. (eds.) Springer Handbook of Speech Processing, pp. 437\u2013455. Springer, Dordrecht (2008)"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Charfuelan, M., Steiner, I.: Expressive speech synthesis in MARY TTS using audiobook data and EmotionML. In: Proceedings of INTERSPEECH (2013)","DOI":"10.21437\/Interspeech.2013-395"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Eyben, F., Buchholz, S., Braunschweiler, N., Latorre, J., Wan, V., Gales, M., Knill, K.: Unsupervised clustering of emotion and voice styles for expressive TTS. In: ICASSP, pp. 4009\u20134012 (2012)","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Peng, D., Wang, L., Chu, M., Chen, Y., Yu, P., Guo, J.: Constructing stylistic synthesis databases from audio books. In: INTERSPEECH, Pittsburgh, PA, USA (2006)","DOI":"10.21437\/Interspeech.2006-485"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Sz\u00e9kely, E., Cabral, J.P., Cahill, P., Carson-Berndsen, J.: Clustering expressive speech styles in audiobooks using glottal source parameters. In: INTERSPEECH, pp. 2409\u20132412 (2011)","DOI":"10.21437\/Interspeech.2011-627"},{"key":"38_CR6","unstructured":"Sz\u00e9kely, E., Cabral, J.P., Abou-Zleikha, M., Cahill, P., Carson-Berndsen, J.: Evaluating expressive speech synthesis from audiobook corpora for conversational phrases. In: Proceedings of LREC 2012 (2012)"},{"key":"38_CR7","unstructured":"Matou\u0161ek, J., Tihelka, D., Romportl, J.: Building of a speech corpus optimised for unit selection TTS synthesis. In: Proceedings of LREC 2008 (2008)"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Prahallad, K., Toth, A.R., Black, A.W.: Automatic building of synthetic voices from large multi-paragraph speech databases. In: INTERSPEECH, pp. 2901\u20132904 (2007)","DOI":"10.21437\/Interspeech.2007-546"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Braunschweiler, N., Buchholz, S.: Automatic sentence selection from speech corpora including diverse speech for improved HMM-TTS synthesis quality. In: INTERSPEECH, pp. 1821\u20131824 (2011)","DOI":"10.21437\/Interspeech.2011-38"},{"key":"38_CR10","unstructured":"Prahallad, K., Black, A.W.: Handling large audio files in audio books for building synthetic voices. In: The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, pp. 148\u2013153, Japan, Kyoto (2010)"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Tihelka, D.: Annotation errors detection in TTS corpora. In: Proceedings of INTERSPEECH, pp. 1511\u20131515, Lyon, France (2013)","DOI":"10.21437\/Interspeech.2013-305"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45510-5_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T16:14:54Z","timestamp":1657210494000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45510-5_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319455099","9783319455105"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45510-5_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}