{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T12:58:00Z","timestamp":1776171480305,"version":"3.50.1"},"reference-count":34,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434617","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":1,"title":["Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs"],"prefix":"10.1109","author":[{"given":"Wei-Cheng","family":"Tseng","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Texas,USA"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Texas,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3207050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref4","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"Baevski","year":"2019","journal-title":"arXiv preprint arXiv:1911.03912"},{"key":"ref5","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"Ling","year":"2020","journal-title":"arXiv preprint arXiv:2012.06659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"Dinosr: Self-distillation and online clustering for self-supervised speech representation learning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv preprint arXiv:1807.03748"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389700"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1176"},{"key":"ref12","article-title":"Sustainable self-supervised learning for speech representations","author":"Lugo","year":"2024","journal-title":"arXiv preprint arXiv:2406.07696"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref14","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref16","article-title":"Speechtokenizer: Unified speech tokenizer for speech language models","author":"Zhang","year":"2023"},{"key":"ref17","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":"ref18","article-title":"Voicebox: Textguided multilingual universal speech generation at scale","author":"Le","year":"2023","journal-title":"arXiv preprint arXiv:2306.07852"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419418"},{"key":"ref21","article-title":"Anygpt: Unified multimodal 11 m with discrete sequence modeling","author":"Zhan","year":"2024","journal-title":"arXiv preprint arXiv:2402.12226"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-330"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446998"},{"key":"ref25","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","volume-title":"arXiv preprint arXiv:2305.16107","author":"Wang","year":"2023"},{"key":"ref26","article-title":"Dasb-discrete audio and speech benchmark","author":"Mousavi","year":"2024","journal-title":"arXiv preprint arXiv:2406.14294"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1510"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-506"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"}],"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\/11434617.pdf?arnumber=11434617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:18Z","timestamp":1775192238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434617","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}