{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:50Z","timestamp":1774419830241,"version":"3.50.1"},"reference-count":33,"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\/icassp49660.2025.10890743","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":["Speech-N-LlaMA: Improving Speech LLMs with Multi-Pass Training"],"prefix":"10.1109","author":[{"given":"Amit Kumar Singh","family":"Yadav","sequence":"first","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gil","family":"Keren","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junteng","family":"Jia","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Mahadeokar","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref5","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Graves"},{"key":"ref6","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref9","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proceeding of the Advances in Neural Information Processing Systems","volume":"27","author":"Sutskever"},{"key":"ref10","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proceeding of the International Conference on Learning Representations","author":"Ranzato"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095826"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-587"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2049"},{"key":"ref15","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proceeding of the Advances in Neural Information Processing Systems","volume":"28","author":"Bengio"},{"key":"ref16","article-title":"Can generative large language models perform asr error correction?","author":"Ma","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref19","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref20","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceeding of the International Conference on Machine Learning","author":"Radford"},{"issue":"3","key":"ref23","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref26","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389751"},{"key":"ref31","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"}],"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\/10890743.pdf?arnumber=10890743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:55Z","timestamp":1774416295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890743","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}