{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:11:50Z","timestamp":1742641910356,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053811","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7239-7243","source":"Crossref","is-referenced-by-count":14,"title":["Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks"],"prefix":"10.1109","author":[{"given":"Kazuhiro","family":"Nakamura","sequence":"first","affiliation":[]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[]},{"given":"Kei","family":"Hashimoto","sequence":"additional","affiliation":[]},{"given":"Keiichiro","family":"Oura","sequence":"additional","affiliation":[]},{"given":"Yoshihiko","family":"Nankaku","sequence":"additional","affiliation":[]},{"given":"Keiichi","family":"Tokuda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2018","key":"ref33","article-title":"Reproducing high-quality singing voice with state-of-the-art AI technology"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2818408"},{"journal-title":"ITU-T Recommendation G 711","article-title":"Pulse code modulation (PCM) of voice frequencies","year":"1988","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref10","article-title":"WaveGlow: A flow- based generative network for speech synthesis","author":"prenger","year":"2018","journal-title":"CoRR"},{"key":"ref11","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proceedings of ICASSP"},{"key":"ref12","first-page":"632","article-title":"Static and dynamic error propagation networks with application to speech coding","author":"robinson","year":"1988","journal-title":"Proceedings of NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref16","first-page":"5500","article-title":"Combining unidirectional long short-term memory with convolutional output layer for highperformance speech synthesis","author":"wang","year":"2017","journal-title":"Proceedings of ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref18","article-title":"A neural parametric singing synthesizer","author":"blaauw","year":"2013","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref6","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"CoRR"},{"key":"ref29","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"key":"ref8","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"CoRR"},{"key":"ref7","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016","journal-title":"CoRR"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proceedings of ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"key":"ref22","first-page":"122","article-title":"Mel log spectral approximation filter for speech synthesis","volume":"j66 a","author":"imai","year":"1983","journal-title":"IEICE Trans Fundamentals (Japanese Edition)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178813"},{"key":"ref24","first-page":"964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proceeding of Interspeech"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472749"},{"key":"ref25","first-page":"2268","article-title":"Prosody contour prediction with long short-term memory, bidirectional, deep recurrent neural networks","author":"fernandez","year":"2014","journal-title":"Proceedings of Interspeech"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053811.pdf?arnumber=9053811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:12:56Z","timestamp":1656375176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053811","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}