{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:52Z","timestamp":1774419952755,"version":"3.50.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890174","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model for Guiding End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yosuke","family":"Higuchi","sequence":"first","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref2","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown"},{"key":"ref5","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Scao","year":"2022","journal-title":"hal-03850124"},{"key":"ref6","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"issue":"240","key":"ref7","first-page":"11 324","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref9","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. ICLR","author":"Wei"},{"key":"ref10","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. NeurIPS","author":"Ouyang"},{"issue":"70","key":"ref11","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-536"},{"key":"ref13","article-title":"ChatGPT or Grammarly? evaluating ChatGPT on grammatical error correction benchmark","author":"Wu","year":"2023"},{"key":"ref14","article-title":"Is ChatGPT a highly fluent grammatical error correction system? a comprehensive evaluation","author":"Fang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"ref16","article-title":"Can generative large language models perform ASR error correction?","author":"Ma","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389637"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref20","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NeurIPS","author":"Chorowski"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref24","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. ICML","author":"Gal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683086"},{"key":"ref30","article-title":"VioLA: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref31","first-page":"18 090","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. NeurIPS","author":"Deshmukh"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref33","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref34","article-title":"X-LLM: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023"},{"key":"ref35","article-title":"Spoken question answering and speech continuation using spectrogram-powered LLM","volume-title":"Proc. ICLR","author":"Nachmani"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1903"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref41","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref42","article-title":"On using monolingual corpora in neural machine translation","author":"Gulcehre","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094796"},{"key":"ref47","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref51","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","volume-title":"Proc. NeurIPS","author":"Xia"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746390"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.402"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389803"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref59","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","volume-title":"Proc. LREC","author":"Rousseau"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890174.pdf?arnumber=10890174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:36Z","timestamp":1774416336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890174","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}