{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:49Z","timestamp":1730230549266,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413396","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6618-6622","source":"Crossref","is-referenced-by-count":1,"title":["Investigation of Fast and Efficient Methods for Multi-Speaker Modeling and Speaker Adaptation"],"prefix":"10.1109","author":[{"given":"Yibin","family":"Zheng","sequence":"first","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhui","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"6184","article-title":"Zero-shot multi-speaker text-to-speech with state-of-the-art neural speaker embeddings","author":"cooper","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","first-page":"3680","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref12","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Modeling multi-speaker latent space to improve neural TTS: Quick enrolling new speaker and enhancing premium voice","author":"deng","year":"2018","journal-title":"arXiv preprint arXiv 1812 11467"},{"key":"ref14","article-title":"Deep speaker: an end-to-end neural speaker embedding system","volume":"650","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1705 02304"},{"key":"ref15","article-title":"Deep Voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"6th International Conference on Learning Representations ICLR 2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref4","article-title":"Uncovering latent style factors for expressive speech synthesis","author":"wang","year":"2017","journal-title":"in INTERSPEECH 2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref6","first-page":"10019","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume":"80","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"article-title":"Sample efficient adaptive text-to-speech","year":"0","author":"chen","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"in INTERSPEECH 2017"},{"key":"ref9","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref22","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"journal-title":"Adam A method for stochastic optimization","year":"2015","author":"kingma","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413396.pdf?arnumber=9413396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:20:42Z","timestamp":1659471642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413396","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}