{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:27:52Z","timestamp":1749619672819},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747032","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6327-6331","source":"Crossref","is-referenced-by-count":3,"title":["MSDTRON: A High-Capability Multi-Speaker Speech Synthesis System for Diverse Data Using Characteristic Information"],"prefix":"10.1109","author":[{"given":"Qinghua","family":"Wu","sequence":"first","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanbo","family":"Shen","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Luan","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"article-title":"Hierarchical generative modeling for controllable speech synthesis","year":"2019","author":"hsu","key":"ref14"},{"article-title":"Few shot adaptive normalization driven multi-speaker speech synthesis","year":"2020","author":"kumar","key":"ref15"},{"key":"ref16","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"article-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref17"},{"key":"ref18","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"ArXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1333"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2793"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ArXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"article-title":"Aishell-3: A multi-speaker mandarin tts corpus and the baselines","year":"2020","author":"shi","key":"ref20"},{"article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","year":"2020","author":"kong","key":"ref21"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747032.pdf?arnumber=9747032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:57Z","timestamp":1660594197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747032","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}