{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:54Z","timestamp":1775229654396,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889794","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Speaking from Coarse to Fine: Improving Neural Codec Language Model via Multi-Scale Speech Coding and Generation"],"prefix":"10.1109","author":[{"given":"Haohan","family":"Guo","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fenglong","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc.,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref5","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref6","article-title":"BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","author":"Lajszczak","year":"2024"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref9","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. NeurIPS","volume":"36","author":"Kumar"},{"key":"ref10","article-title":"Attention sorting combats recency bias in long context language models","author":"Peysakhovich","year":"2023"},{"key":"ref11","article-title":"Eliminating position bias of language models: A mechanistic approach","author":"Wang","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3272470"},{"key":"ref13","article-title":"VALL-E R: Robust and efficient zero-shot text-to-speech synthesis via monotonic alignment","author":"Han","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890943"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832247"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1559"},{"key":"ref18","first-page":"14866","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume-title":"Proc. NeurIPS","author":"Razavi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-952"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref21","article-title":"Neural discrete representation learning","volume-title":"Proc. NeurIPS","author":"van den Oord"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s101211259"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref24","article-title":"Simple and controllable music generation","volume-title":"Proc. NeurIPS","volume":"36","author":"Copet"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1192"},{"key":"ref26","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024"},{"key":"ref27","article-title":"Seed-TTS: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024"},{"key":"ref28","article-title":"CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref30","article-title":"Mega-TTS 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"Proc. ICLR","author":"Jiang"},{"key":"ref31","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref32","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref33","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889794.pdf?arnumber=10889794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:19Z","timestamp":1774416379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889794","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}