{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:38Z","timestamp":1775199638838,"version":"3.50.1"},"reference-count":40,"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\/asru65441.2025.11434618","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Analysing the Language of Neural Audio Codecs"],"prefix":"10.1109","author":[{"given":"Joonyong","family":"Park","sequence":"first","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"David M.","family":"Chan","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Shunsuke","family":"Kando","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643619"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref6","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-330"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-337"},{"key":"ref10","article-title":"Human behavior and the principle of least effort","author":"Zipf","year":"1949"},{"key":"ref11","first-page":"3","article-title":"Contribution \u00e0 la th\u00e9orie math\u00e9matique des jeux de communication","volume":"2","author":"Mandelbrot","year":"1953","journal-title":"Annales de l\u2019ISUP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44686-9_33"},{"key":"ref13","article-title":"Information retrieval: Computational and theoretical aspects","author":"Heaps","year":"1978"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1951.tb01366.x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448331"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref17","article-title":"Visual instruction tuning","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref18","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref23","article-title":"Towards audio language modeling - an overview","author":"Wu","year":"2024","journal-title":"arXiv preprint 2402.13236"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2441"},{"key":"ref26","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref28","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models, 2016 [sound]","author":"Valentini-Botinhao","year":"2017"},{"key":"ref29","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref31","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"Proc. ICML","author":"Bogdanov"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref34","first-page":"10330","article-title":"Codec-SUPERB: An indepth analysis of sound codec models","volume-title":"Findings of ACL","author":"Wu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref36","article-title":"Analyzing the language of visual tokens","author":"Chan","year":"2024","journal-title":"arXiv preprint arXiv:2411.05001"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/070710111"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2280095"},{"key":"ref39","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"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\/11434618.pdf?arnumber=11434618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:16Z","timestamp":1775192236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434618","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}