{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:52:45Z","timestamp":1768413165690,"version":"3.49.0"},"reference-count":26,"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\/iscslp63861.2024.10800681","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"496-500","source":"Crossref","is-referenced-by-count":1,"title":["The Codec Language Model-Based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024"],"prefix":"10.1109","author":[{"given":"Shuoyi","family":"Zhou","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Yixuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Weiqing","family":"Li.","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Runchuan","family":"Ye","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Weihao","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Zijian","family":"Lin","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Shun","family":"Lei","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"International Conference on Learning Representations","author":"Ping","year":"2018"},{"key":"ref2","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume-title":"In-ternational Conference on Learning Representations","author":"Chen"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419418"},{"key":"ref7","article-title":"Ella-v: Stable neural codec language modeling with alignment-guided sequence reordering","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-259"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445828"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-412"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1989"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref17","first-page":"483","article-title":"mt5: A massively multilingual pretrained text-to-text transformer","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Xue"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref23","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Stay on topic with classifier-free guidance","author":"Sanchez","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681680"}],"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\/10800681.pdf?arnumber=10800681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:38Z","timestamp":1735021598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800681","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}