{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:47:03Z","timestamp":1768423623855,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800694","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"506-510","source":"Crossref","is-referenced-by-count":2,"title":["The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings"],"prefix":"10.1109","author":[{"given":"Kangxiang","family":"Xia","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Dake","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Jixun","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Liumeng","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong,Shenzhen"}]},{"given":"Hanzhao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data (SRIBD)"}]},{"given":"Zhao","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"}]},{"given":"Qingqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Magic data"}]},{"given":"Lei","family":"Luo","sequence":"additional","affiliation":[{"name":"Magic data"}]},{"given":"Minghui","family":"Dong","sequence":"additional","affiliation":[{"name":"Insitutue for Infocomm Research (I2R)"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"China Computer Federation"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","author":"Ren","year":"2019"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim","year":"2021"},{"key":"ref4","article-title":"Better speech synthesis through scaling","volume-title":"arXiv preprint","author":"Betker","year":"2023"},{"key":"ref5","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445828"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1989"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-412"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref11","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2021-14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref14","article-title":"Simple and controllable music generation","author":"Copet","year":"2023","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref16","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR. OpenRe-view. net"},{"key":"ref17","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref19","first-page":"4485","article-title":"Transferleaming from speaker verification to multispeaker text-to-speech syn-thesis","volume-title":"NeurIPS","author":"Jia","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref21","article-title":"High fidelity neural audio compression","volume":"2023","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1559"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095105"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800694.pdf?arnumber=10800694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:34:09Z","timestamp":1735022049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800694","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}