{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:55:38Z","timestamp":1742928938218,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319281070"},{"type":"electronic","value":"9783319281094"}],"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-28109-4_12","type":"book-chapter","created":{"date-parts":[[2016,1,22]],"date-time":"2016-01-22T07:03:21Z","timestamp":1453446201000},"page":"117-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Constructing a Deep Neural Network Based Spectral Model for Statistical Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Shinji","family":"Takaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,1,23]]},"reference":[{"key":"12_CR1","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":"12_CR2","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1109\/TASL.2013.2269291","volume":"21","author":"Z-H Ling","year":"2013","unstructured":"Ling, Z.-H., Deng, L., Yu, D.: Modeling spectral envelopes using restricted Boltzmann machines and deep belief networks for statistical parametric speech synthesis. IEEE Trans. Audio Speech Lang. Process. 21, 2129\u20132139 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Fan, Y., Qian, Y., Xie, F., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proceedings of Interspeech, pp. 1964\u20131968 (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Fernandez, R., Rendel, A., Ramabhadran, B., Hoory, R.: Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks. In: Proceedings of Interspeech, pp. 2268\u20132272 (2014)","DOI":"10.21437\/Interspeech.2014-445"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Vishnubhotla, R., Fernandez, S., Ramabhadran, B.: An autoencoder neural-network based low-dimensionality approach to excitation modeling for hmm-based text-to-speech. In: Proceedings of ICASSP, pp. 4614\u20134617 (2010)","DOI":"10.1109\/ICASSP.2010.5495546"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.-H., Raitio, T., Valentini-Botinhao, C., Yamagishi, J., Ling, Z.-H.: DNN-based stochastic postfilter for HMM-based speech synthesis. In: Proceedings of Interspeech, pp. 1954\u20131958 (2014)","DOI":"10.21437\/Interspeech.2014-441"},{"key":"12_CR7","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., Cheveigne, 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 Commun. 27, 187\u2013207 (1999)","journal-title":"Speech Commun."},{"key":"12_CR8","unstructured":"Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. Citeseer (2001)"},{"issue":"10","key":"12_CR9","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.tics.2007.09.004","volume":"11","author":"Geoffrey E. Hinton","year":"2007","unstructured":"Hinton, G.E.: Learning multiple layers of representation. Trends Cogn. Sci. 11, 428\u2013434 (2007)","journal-title":"Trends in Cognitive Sciences"},{"issue":"5786","key":"12_CR10","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G. E. Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318\u2013362 (1986)","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"12_CR12","unstructured":"Muthukumar, P.K., Black, A.: A deep learning approach to data-driven parameterizations for statistical parametric speech synthesis (2014). arXiv:1409.8558"},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen, H., Tokuda, K., Black, A.W.: Statistical parametric speech synthesis. Speech Commun. 51, 1039\u20131064 (2009)","journal-title":"Speech Commun."},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Richmond, K., Clark, R., Fitt, S.: On generating combilex pronunciations via morphological analysis. In: Proceedings of Interspeech, pp. 1974\u20131977 (2010)","DOI":"10.21437\/Interspeech.2010-560"}],"container-title":["Smart Innovation, Systems and Technologies","Recent Advances in Nonlinear Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-28109-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T04:50:14Z","timestamp":1654145414000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-28109-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319281070","9783319281094"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-28109-4_12","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"23 January 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}