{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:54Z","timestamp":1775200014167,"version":"3.50.1"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434720","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning"],"prefix":"10.1109","author":[{"given":"Jiatong","family":"Shi","sequence":"first","affiliation":[{"name":"CMU"}]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"SJTU"}]},{"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"CMU"}]},{"given":"Chenda","family":"Li","sequence":"additional","affiliation":[{"name":"SJTU"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"SJTU"}]},{"given":"Jinchuan","family":"Tian","sequence":"additional","affiliation":[{"name":"CMU"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"CMU"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643619"},{"key":"ref3","article-title":"Towards audio language modeling-an overview","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2402.13236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref6","volume-title":"Opus codec: The standard for interactive speech and audio transmission over the Internet","author":"Valin","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832289"},{"key":"ref10","article-title":"CosyVoice 2: Scalable streaming speech synthesis with large language models","volume-title":"arXiv preprint arXiv:2412.10117","author":"Du","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-demo.12"},{"key":"ref12","first-page":"47704","article-title":"Simple and controllable music generation","volume-title":"Proc. NeurIPS","volume":"36","author":"Copet"},{"key":"ref13","article-title":"BigCodec: Pushing the limits of low-bitrate neural speech codec","author":"Xin","year":"2024","journal-title":"arXiv preprint arXiv:2409.05377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888202"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-288"},{"key":"ref18","article-title":"CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2407.05407"},{"key":"ref19","article-title":"Spectral codecs: Spectrogram-based audio codecs for high quality speech synthesis","volume-title":"arXiv preprint arXiv:2406.05298","author":"Langman","year":"2024"},{"key":"ref20","article-title":"Scaling transformers for low-bitrate highquality speech coding","volume-title":"Proc. ICML","author":"Parker"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-921"},{"key":"ref22","article-title":"WavTokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling","author":"Ji","year":"2024","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094723"},{"key":"ref27","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.562"},{"key":"ref29","first-page":"22605","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML.","author":"Ju"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447523"},{"key":"ref31","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2305.02765"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3469530"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446556"},{"key":"ref34","article-title":"Language-Codec: Reducing the gaps between discrete codec representation and speech language models","author":"Ji","year":"2024","journal-title":"arXiv preprint arXiv:2402.12208"},{"key":"ref35","article-title":"UniAudio 1.5: Large language model-driven audio codec is a few-shot audio task learner","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref36","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv preprint arXiv:2410.00037"},{"key":"ref37","article-title":"SNAC: Multi-scale neural audio codec","author":"Siuzdak","year":"2024","journal-title":"arXiv preprint arXiv:2410.14411"},{"key":"ref38","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/83.480761"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.197157"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1239"},{"key":"ref43","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1938"},{"key":"ref45","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3378602"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref50","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proc. ISMIR","author":"Fonseca"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref53","article-title":"Scale this, not that: Investigating key dataset attributes for efficient speech enhancement scaling","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2412.14890"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-demo.19"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-439"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref59","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"Proc. ICML. PMLR, 2023","author":"Radford"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434720.pdf?arnumber=11434720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:43Z","timestamp":1775192323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434720","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}