{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:47:00Z","timestamp":1771516020287,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094777","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation"],"prefix":"10.1109","author":[{"given":"Qi","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Media Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414438"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053139"},{"key":"ref15","article-title":"Dynamic-programming approach to continuous speech recognition","author":"sakoe","year":"1971","journal-title":"1971 Proc the International Congress of Acoustics"},{"key":"ref14","article-title":"Soft-dtw: a differentiable loss function for time-series","author":"cuturi","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref11","author":"du","year":"2022","journal-title":"Vqtts High-fidelity text-to-speech synthesis with self-supervised vq acoustic feature"},{"key":"ref10","author":"du","year":"2021","journal-title":"Rich prosody diversity modelling with phone-level mixture density network"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13382"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","author":"hannun","year":"2014","journal-title":"Deep speech Scaling up end-to-end speech recognition"},{"key":"ref24","author":"ma","year":"2022","journal-title":"MT4SSL Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets"},{"key":"ref23","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"Using dynamic time warping to find patterns in time series","author":"berndt","year":"1994","journal-title":"KDD Workshop"},{"key":"ref25","author":"yang","year":"2021","journal-title":"Superb Speech processing universal performance benchmark"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref22","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","author":"baevski","year":"2019","journal-title":"vq-wav2vec Self-supervised learning of discrete speech representations"},{"key":"ref28","author":"du","year":"2018","journal-title":"AISHELL-2 Transforming Mandarin ASR Research Into Industrial Scale"},{"key":"ref27","article-title":"Chinese speech pretrained models from tencent game mate","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref9","author":"ren","year":"2020","journal-title":"Fastspeech 2 Fast and high-quality end-to-end text to speech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747495"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094777.pdf?arnumber=10094777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:26:38Z","timestamp":1769487998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094777","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}