{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:21:57Z","timestamp":1775838117570,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Singapore","isbn-type":[{"value":"9789811505942","type":"print"},{"value":"9789811505959","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,11,23]],"date-time":"2019-11-23T00:00:00Z","timestamp":1574467200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-981-15-0595-9_3","type":"book-chapter","created":{"date-parts":[[2019,11,22]],"date-time":"2019-11-22T17:02:36Z","timestamp":1574442156000},"page":"39-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Text-to-Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Yoshinori","family":"Shiga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfu","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kentaro","family":"Tachibana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,23]]},"reference":[{"issue":"3","key":"3_CR1","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1121\/1.383940","volume":"67","author":"DH Klatt","year":"1980","unstructured":"Klatt, D.H.: Software for a cascade\/parallel formant synthesizer. J. Acoust. Soc. Am. 67(3), 971\u2013995 (1980)","journal-title":"J. Acoust. Soc. Am."},{"issue":"5","key":"3_CR2","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E Moulines","year":"1990","unstructured":"Moulines, E., Charpentier, F.: Pitch synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Commun. 9(5), 453\u2013467 (1990)","journal-title":"Speech Commun."},{"key":"3_CR3","unstructured":"Black, A.W., Campbell, N.: Optimising selection of units from speech databases for concatenative synthesis. In: Proceedings of Eurospeech95, vol. 1, pp. 581\u2013584. Madrid, Spain (1995)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Simultaneous modeling of spectrum, pitch and duration in HMM-Based Speech Synthesis. In: Proceeding of Eurospeech, vol. 5, pp. 2347\u20132350 (1999)","DOI":"10.21437\/ICSLP.1998-6"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: A hidden semi-Markov model-based speech synthesis system. IEICE Transactions on Information and Systems, E90-D(5), 825\u2013834 (2007)","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Ni, J., Shiga, Y., Kawai, H.: Global syllable vectors for building TTS front-end with deep learning. In: Proceedings of INTERSPEECH2017, pp. 769\u2013773 (2017)","DOI":"10.21437\/Interspeech.2017-669"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. http:\/\/nlp.stanford.edu\/projects\/glove\/ 2014","DOI":"10.3115\/v1\/D14-1162"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Irsory, O., Cardie, C.: Opinion mining with deep recurrent neural networks. In: Proceedings of the 2014 conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 720\u2013728 (2014)","DOI":"10.3115\/v1\/D14-1080"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: Proceedings of ICASSP, pp. 7962\u20137966 (2013)","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., Kitamura, T.: Speech parameter generation algorithms for HMM-based speech synthesis. In: Proceedings of ICASSP, pp. 1315\u20131318 (2000)","DOI":"10.21437\/Eurospeech.2001-539"},{"key":"3_CR11","unstructured":"van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., Kavukcuoglu, K.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016). (Unreviewed manuscript)"},{"key":"3_CR12","unstructured":"Mehri, S., Kumar, K., Gulrajani, I., Kumar, R., Jain, S., Sotelo, J., Courville, A., Bengio, Y.: SampleRNN: an unconditional end-to-end neural audio generation model. In: Proceedings of ICLR (2017)"},{"key":"3_CR13","unstructured":"Sotelo, J., Mehri, S., Kumar, K., Santos, J.F., Kastner, K., Courville, A., Bengio, Y.: Char2wav: end-to-end speech synthesis. In: Proceedings of ICLR (2017)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Skerry-Ryan, R.J., Stanton, D., Wu, Y., Weiss, R., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., Le, Q., Agiomyrgiannakis, Y., Clark, R., Saurous, R.A.: Tacotron: towards end-to-end speech synthesis. In: Proceedings of Interspeech, pp. 4006\u20134010 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"3_CR15","unstructured":"Arik, S.O., Chrzanowski, M., Coates, A., Diamos, G., Gibiansky, A., Kang, Y., Li, X., Miller, J., Ng, A., Raiman, J., Sengupta, S., Shoeybi, M.: Deep voice: real-time neural text-to-speech. In Proceedings of ICML, pp. 195\u2013204 (2017)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., Toda, T.: Speaker-dependent WaveNet vocoder. In: Proceedings of Interspeech, pp. 1118\u20131122 (2017)","DOI":"10.21437\/Interspeech.2017-314"},{"key":"3_CR17","unstructured":"ITU-T: Recommendation G. 711. Pulse Code Modulation (PCM) of voice frequencies (1988)"},{"key":"3_CR18","unstructured":"van den Oord, A., Li, Y., Babuschkin, I., Simonyan, K., Vinyals, O., Kavukcuoglu, K., van den Driessche, G., Lockhart, E., Cobo, L.C., Stimberg, F., Casagrande, N., Grewe, D., Noury, S., Dieleman, S., Elsen, E., Kalchbrenner, N., Zen, H., Graves, A., King, H., Walters, T., Belov, D., Hassabis, D.: Parallel WaveNet: fast high-fidelity speech synthesis. arXiv preprint arXiv:1711.10433 (2017). (Unreviewed manuscript)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Okamoto, T., Tachibana, K., Toda, T., Shiga, Y., Kawai, H.: Subband WaveNet with overlapped single-sideband filter- banks. In: Proceedings of ASRU, pp. 698\u2013704 (2017)","DOI":"10.1109\/ASRU.2017.8269005"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Okamoto, T., Tachibana, K., Toda, T., Shiga, Y., Kawai, H.: An investigation of subband WaveNet vocoder covering entire auditory frequency range with limited acoustic features. In: Proceedings of ICASSP, pp. 5654\u20135658 (2018)","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"3_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(83)90013-0","volume-title":"Multirate Digital Signal Processing","author":"RE Crociere","year":"1983","unstructured":"Crociere, R.E., Rabiner, L.R.: Multirate Digital Signal Processing. Prentice Hall, Englewood Cliffs (1983)"}],"container-title":["SpringerBriefs in Computer Science","Speech-to-Speech Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-0595-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T19:24:11Z","timestamp":1665084251000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-0595-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,23]]},"ISBN":["9789811505942","9789811505959"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-0595-9_3","relation":{},"ISSN":["2191-5768","2191-5776"],"issn-type":[{"value":"2191-5768","type":"print"},{"value":"2191-5776","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,23]]},"assertion":[{"value":"23 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}