{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:08:39Z","timestamp":1775200119414,"version":"3.50.1"},"reference-count":33,"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\/asru65441.2025.11434740","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":["Evaluating Self-Supervised Speech Models Via Text-Based LLMs"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Maekaku","sequence":"first","affiliation":[{"name":"LY Corporation,Tokyo,JAPAN"}]},{"given":"Keita","family":"Goto","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,JAPAN"}]},{"given":"Jinchuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]},{"given":"Yusuke","family":"Shinohara","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,JAPAN"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref9","first-page":"8479","article-title":"SUPERBSG: Enhanced speech processing universal performance benchmark for semantic and generative capabilities","volume-title":"Proc. ACL","author":"Tsai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101695"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref15","article-title":"Insights on representational similarity in neural networks with canonical correlation","author":"Morcos","year":"2018","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023","journal-title":"Authorea Preprints"},{"key":"ref21","article-title":"STAB: Speech tokenizer assessment benchmark","author":"Vashishth","year":"2024","journal-title":"arXiv preprint arXiv:2409.02384"},{"key":"ref22","article-title":"Starcoder: May the source be with you!","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2305.06161"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"},{"key":"ref24","volume-title":"Gemma 3 technical report","author":"Kamath","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"ref27","article-title":"Qwen3 technical report","volume-title":"arXiv preprint arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref28","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras","volume-title":"arXiv preprint arXiv:2503.01743","author":"Abouelenin","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref31","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"}],"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\/11434740.pdf?arnumber=11434740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:05Z","timestamp":1775192345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434740","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}