{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:27Z","timestamp":1772907747144,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832247","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"645-651","source":"Crossref","is-referenced-by-count":6,"title":["SoCodec: A Semantic-Ordered Multi-Stream Speech Codec For Efficient Language Model Based Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Haohan","family":"Guo","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Fenglong","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc.,Shanghai,China"}]},{"given":"Kun","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc.,Shanghai,China"}]},{"given":"Dongchao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Dake","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi’an,China"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","year":"2023"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref4","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023","journal-title":"arXiv preprint arXiv:2305.07243"},{"key":"ref5","article-title":"BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","author":"Lajszczak","year":"2024","journal-title":"arXiv preprint arXiv:2402.08093"},{"key":"ref6","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref7","article-title":"HiFi-Codec: Groupresidual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2305.02765"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","article-title":"\u2019Simple and controllable music generation","volume-title":"Proc. NeurIPS","volume":"36","author":"Copet"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448454"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1559"},{"key":"ref12","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju"},{"key":"ref13","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2308.16692"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref16","article-title":"Learning ordered representations with nested dropout","author":"Rippel","year":"2014","journal-title":"arXiv preprint arXiv:1402.0915"},{"key":"ref17","article-title":"Anytime sampling for autoregressive models via ordered autoencoding","volume-title":"Proc. ICLR","author":"Xu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-941"},{"key":"ref21","article-title":"Mega-TTS 2: Zero-shot text-to-speech with arbitrary length speech prompts","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2307.07218"},{"key":"ref22","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref23","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref25","article-title":"Chinese speech pretrain","author":"Guo","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832247.pdf?arnumber=10832247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:22Z","timestamp":1737398362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832247","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}