{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:17:16Z","timestamp":1780672636606,"version":"3.54.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448022","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10176-10180","source":"Crossref","is-referenced-by-count":3,"title":["Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems"],"prefix":"10.1109","author":[{"given":"Takuma","family":"Udagawa","sequence":"first","affiliation":[{"name":"IBM Research AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayuki","family":"Suzuki","sequence":"additional","affiliation":[{"name":"IBM Research AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gakuto","family":"Kurata","sequence":"additional","affiliation":[{"name":"IBM Research AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayasu","family":"Muraoka","sequence":"additional","affiliation":[{"name":"IBM Research AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[{"name":"IBM Research AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref3","article-title":"Gpt-4 technical report","year":"2023","journal-title":"ArXiv"},{"key":"ref4","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W18-5446","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"ICLR","author":"Wang"},{"key":"ref6","article-title":"Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation","volume-title":"ICML","author":"Hu"},{"key":"ref7","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown"},{"key":"ref8","article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurIPS","author":"Ouyang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref10","article-title":"Speech recognition by simply finetuning bert","volume-title":"ICASSP","author":"Huang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095186"},{"key":"ref13","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref14","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746801"},{"key":"ref18","article-title":"A context-aware knowledge transferring strategy for ctc-based asr","author":"Lu","year":"2022","journal-title":"IEEE SLT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747887"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1441"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.729"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref28","article-title":"Effective sentence scoring method using bert for speech recognition","volume-title":"ACML","author":"Shin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-739"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8181-6_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.103"},{"key":"ref41","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448022.pdf?arnumber=10448022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:50:34Z","timestamp":1722574234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448022","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}