{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:55Z","timestamp":1775200315813,"version":"3.50.1"},"reference-count":22,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/asru65441.2025.11434796","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Guanyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Bohan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Hankun","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Yiwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Zhihan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434425"},{"key":"ref3","article-title":"GenSE: Generative speech enhancement via language models using hierarchical modeling","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref4","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref6","article-title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models","volume-title":"International Conference on Learning Representations","author":"Zhang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34761"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643619"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","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":"ref12","article-title":"CodecSUPERB: An in-depth analysis of sound codec models","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2402.13071"},{"key":"ref13","article-title":"DASB-Discrete Audio and Speech Benchmark","author":"Mousavi","year":"2024","journal-title":"arXiv preprint arXiv:2406.14294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref18","article-title":"The 4th CHiME speech separation and recognition challenge","author":"Vincent","year":"2018"},{"key":"ref19","first-page":"28492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"International Conference on Machine Learning.","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-demo.19"}],"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\/11434796.pdf?arnumber=11434796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:52Z","timestamp":1775192392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434796","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}