{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:19:30Z","timestamp":1743031170102,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319393926"},{"type":"electronic","value":"9783319393933"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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\/978-3-319-39393-3_28","type":"book-chapter","created":{"date-parts":[[2016,5,20]],"date-time":"2016-05-20T15:24:36Z","timestamp":1463757876000},"page":"280-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["LSTM Deep Neural Networks Postfiltering for Improving the Quality of Synthetic Voices"],"prefix":"10.1007","author":[{"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"first","affiliation":[]},{"given":"John","family":"Goddard-Close","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,5,21]]},"reference":[{"issue":"5","key":"28_CR1","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/JPROC.2013.2251852","volume":"101","author":"K Tokuda","year":"2013","unstructured":"Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., Oura, K.: Speech synthesis based on hidden markov models. Proc. IEEE 101(5), 1234\u20131252 (2013)","journal-title":"Proc. IEEE"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Black, A.W.: Unit selection and emotional speech. In: Interspeech (2003)","DOI":"10.21437\/Eurospeech.2003-473"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Yoshimura, T., Tokuda, T., Masuko, T., Kobayashi, T., Kitamura, T.: Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In: Proceedings of the Eurospeech, pp. 2347\u20132350 (1999)","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Falaschi, A., Giustiniani, M., Verola, M.: A hidden markov model approach to speech synthesis. In: Proceedings of the Eurospeech, pp. 2187\u20132190 (1989)","DOI":"10.21437\/Eurospeech.1989-179"},{"key":"28_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/978-3-540-87391-4_45","volume-title":"Text, Speech and Dialogue","author":"S Karabetsos","year":"2008","unstructured":"Karabetsos, S., Tsiakoulis, P., Chalamandaris, A., Raptis, S.: HMM-based speech synthesis for the greek language. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2008. LNCS (LNAI), vol. 5246, pp. 349\u2013356. Springer, Heidelberg (2008)"},{"issue":"2","key":"28_CR6","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.specom.2009.09.004","volume":"52","author":"M Pucher","year":"2010","unstructured":"Pucher, M., Schabus, D., Yamagishi, Y., Neubarth, F., Strom, V.: Modeling and interpolation of austrian german and viennese dialect in HMM-based speech synthesis. Speech Commun. 52(2), 164\u2013179 (2010)","journal-title":"Speech Commun."},{"key":"28_CR7","unstructured":"Erro, D., Sainz, I., Luengo, I., Odriozola, I., S\u00e1nchez, J., Saratxaga, I., Navas, E., Hern\u00e1ez, I.: HMM-based speech synthesis in basque language using HTS. In: Proceedings of the FALA (2010)"},{"issue":"3","key":"28_CR8","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/j.specom.2010.12.002","volume":"53","author":"A Stan","year":"2011","unstructured":"Stan, A., Yamagishi, Y., King, S., Aylett, M.: The romanian speech synthesis (RSS) corpus: building a high quality HMM-based speech synthesis system using a high sampling rate. Speech Commun. 53(3), 442\u2013450 (2011)","journal-title":"Speech Commun."},{"key":"28_CR9","first-page":"13","volume":"12","author":"T Kuczmarski","year":"2010","unstructured":"Kuczmarski, T.: HMM-based speech synthesis applied to polish. Speech Lang. Technol. 12, 13 (2010)","journal-title":"Speech Lang. Technol."},{"key":"28_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-3-642-15760-8_37","volume-title":"Text, Speech and Dialogue","author":"Z Hanzl\u00ed\u010dek","year":"2010","unstructured":"Hanzl\u00ed\u010dek, Z.: Czech HMM-based speech synthesis. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS, vol. 6231, pp. 291\u2013298. Springer, Heidelberg (2010)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Pan, S., Tao, J.: HMM-based speech synthesis with a flexible mandarin stress adaptation model. In: Proceedings of the 10th ICSP2010 Proceedings, Beijing, pp. 625\u2013628 (2010)","DOI":"10.1109\/ICOSP.2010.5656769"},{"issue":"1","key":"28_CR12","first-page":"1","volume":"2","author":"ST Phan","year":"2013","unstructured":"Phan, S.T., Vu, T.T., Duong, C.T., Luong, M.C.: A study in vietnamese statistical parametric speech synthesis based on HMM. Int. J. 2(1), 1\u20136 (2013)","journal-title":"Int. J."},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Boothalingam, R., Sherlin, S.V., Gladston, A.R., Christina, S.L., Vijayalakshmi, P., Thangavelu, N., Murthy, H.A.: Development and evaluation of unit selection and HMM-based speech synthesis systems for Tamil. In: National Conference on Communications (NCC), pp. 1\u20135. IEEE (2013)","DOI":"10.1109\/NCC.2013.6487984"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Khalil, K.M., Adnan, C.: Implementation of speech synthesis based on HMM using PADAS database. In: 12th International Multi-Conference on Systems, Signals & Devices (SSD), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/SSD.2015.7348133"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Nakamura, K., Oura, K., Nankaku, Y., Tokuda, K.: HMM-based singing voice synthesis and its application to japanese and english. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 265\u2013269 (2014)","DOI":"10.1109\/ICASSP.2014.6853599"},{"key":"28_CR16","unstructured":"Roekhaut, S., Brognaux, S., Beaufort, R., Dutoit, T.: Elite-HTS: a NLP tool for French HMM-based speech synthesis. In: Interspeech, pp. 2136\u20132137 (2014)"},{"key":"28_CR17","unstructured":"HMM-based Speech Synthesis System (HTS). http:\/\/hts.sp.nitech.ac.jp\/"},{"issue":"11","key":"28_CR18","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.1109\/TASLP.2015.2461448","volume":"23","author":"LH Chen","year":"2015","unstructured":"Chen, L.H., Raitio, T., Valentini-Botinhao, C., Ling, Z.H., Yamagishi, J.: A deep generative architecture for postfiltering in statistical parametric speech synthesis. IEEE\/ACM Trans. Audio, Speech Lang. Process. (TASLP) 23(11), 2003\u20132014 (2015)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process. (TASLP)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Takamichi, S., Toda, T., Neubig, G., Sakti, S., Nakamura, S.: A postfilter to modify the modulation spectrum in HMM-based speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 290\u2013294 (2014)","DOI":"10.1109\/ICASSP.2014.6853604"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Takamichi, S., Toda, T., Black, A.W., Nakamura, S.: Modified post-filter to recover modulation spectrum for HMM-based speech synthesis. In: IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 547\u2013551 (2014)","DOI":"10.1109\/GlobalSIP.2014.7032177"},{"key":"28_CR21","unstructured":"Prasanna, K.M., Black, A.W.: Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis. arXiv preprint (2016). arXiv:1601.07215"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Interspeech, pp. 1964\u20131968 (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Zen, H., Sak, H.: Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4470\u20134474 (2015)","DOI":"10.1109\/ICASSP.2015.7178816"},{"issue":"8","key":"28_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., Mohamed, A.: Hybrid speech recognition with deep bidirectional LSTM. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (2013)","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"28_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"A Graves","year":"2005","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799\u2013804. Springer, Heidelberg (2005)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Erro, D., Sainz, I., Navas, E., Hernaez, I.: Improved HNM-based vocoder for statistical synthesizers. In: InterSpeech, pp. 1809\u20131812 (2011)","DOI":"10.21437\/Interspeech.2011-35"},{"key":"28_CR28","unstructured":"Kominek, J., Black, A.W.: The CMU Arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2013)","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A.: Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014)","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"28_CR31","unstructured":"Kominek, J., Schultz, T., Black, A.W.: Synthesizer voice quality of new languages calibrated with mean mel cepstral distortion. In: SLTU (2008)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-39393-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T11:07:35Z","timestamp":1692356855000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-39393-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319393926","9783319393933"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-39393-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"21 May 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}