{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:32:45Z","timestamp":1776889965279,"version":"3.51.2"},"reference-count":43,"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\/asru65441.2025.11434801","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":2,"title":["Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hao","family":"Shi","sequence":"first","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Tomoya","family":"Mizumoto","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Lianbo","family":"Liu","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Atsushi","family":"Kojima","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Yui","family":"Sudo","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832362"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887642"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682822"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038197"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407511"},{"key":"ref8","first-page":"438","article-title":"Spectrograms fusion-based end-to-end robust automatic speech recognition","volume-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Shi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11426"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448116"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref20","article-title":"Roberta: A robustly optimized bert pretraining approach","volume":"364","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Association for Computational Linguistics (NAACL)"},{"key":"ref22","article-title":"Improving language understanding with unsupervised learning","volume-title":"Technical report, OpenAI","author":"Radford","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref24","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"Yang","year":"2019","journal-title":"arXiv preprint arXiv:1906.08237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref26","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref27","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":"ref28","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chorowski"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"issue":"2","key":"ref30","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096630"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Exploration of adapter for noise robust automatic speech recognition","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv:2402.18275"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-270"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref37","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv:2005.11262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389752"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095295"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"}],"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\/11434801.pdf?arnumber=11434801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:54Z","timestamp":1775192394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434801","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}