{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:39:56Z","timestamp":1774589996765,"version":"3.50.1"},"reference-count":19,"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\/icassp39728.2021.9413880","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"8588-8592","source":"Crossref","is-referenced-by-count":35,"title":["Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Chung-Ming","family":"Chien","sequence":"first","affiliation":[{"name":"National Taiwan University College of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jheng-Hao","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University College of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien-yu","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University College of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-chun","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University College of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University College of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref11","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref13","author":"li","year":"2020","journal-title":"Controllable emotion transfer for end-to-end speech synthesis"},{"key":"ref14","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume":"2019","author":"hsu","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref18","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"ArXiv"},{"key":"ref19","first-page":"498","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017"},{"key":"ref4","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"0"},{"key":"ref3","article-title":"The multi-speaker multi-style voice cloning challenge 2021","author":"xie","year":"2021","journal-title":"2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","article-title":"Sample efficient adaptive text-to-speech","volume":"2019","author":"chen","year":"0"},{"key":"ref5","first-page":"10019","article-title":"Neural voice cloning with a few samples","volume":"31","author":"arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref7","author":"park","year":"2019","journal-title":"Multi-speaker end-to-end speech synthesis"},{"key":"ref2","author":"ren","year":"2020","journal-title":"Fastspeech 2 Fast and high-quality end-to-end text to speech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09413880.pdf?arnumber=9413880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:17:40Z","timestamp":1659485860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413880","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}