{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:48:35Z","timestamp":1780318115462,"version":"3.54.1"},"reference-count":40,"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\/icassp49660.2025.10887642","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"],"prefix":"10.1109","author":[{"given":"Lingwei","family":"Meng","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoqing","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuejiao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref2","author":"Touvron","year":"2023","journal-title":"LLaMA: Open and efficient foundation language models"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref4","author":"Chen","year":"2024","journal-title":"Next token prediction towards multimodal intelligence: A comprehensive survey"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref6","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref7","author":"Chu","year":"2024","journal-title":"Qwen2-audio technical report"},{"key":"ref8","article-title":"Language is not all you need: Aligning perception with language models","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Huang"},{"key":"ref9","article-title":"Grounding multimodal large language models to the world","volume-title":"The Twelfth International Conference on Learning Representations","author":"Peng"},{"key":"ref10","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pan"},{"key":"ref11","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref12","volume-title":"Autoregressive speech synthesis without vector quantization","author":"Meng","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2988423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095295"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3318398"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888841"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3487795"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1640"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1062"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1422"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-971"},{"key":"ref30","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446249"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-1"},{"key":"ref39","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"}],"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\/10887642.pdf?arnumber=10887642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:20Z","timestamp":1774416260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887642","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}