{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:20:41Z","timestamp":1776889241362,"version":"3.51.2"},"reference-count":39,"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\/asru65441.2025.11434651","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities"],"prefix":"10.1109","author":[{"given":"George","family":"Saon","sequence":"first","affiliation":[{"name":"IBM Research"}]},{"given":"Avihu","family":"Dekel","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Alexander","family":"Brooks","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Tohru","family":"Nagano","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Abraham","family":"Daniels","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Aharon","family":"Satt","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Ashish","family":"Mittal","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"David","family":"Haws","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Edmilson","family":"Morais","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Gakuto","family":"Kurata","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Hagai","family":"Aronowitz","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Ibrahim","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Jeff","family":"Kuo","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Kate","family":"Soule","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Luis","family":"Lastras","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Masayuki","family":"Suzuki","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Ron","family":"Hoory","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Sashi","family":"Novitasari","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Takashi","family":"Fukuda","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Vishal","family":"Sunder","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Xiaodong","family":"Cui","sequence":"additional","affiliation":[{"name":"IBM Research"}]},{"given":"Zvi","family":"Kons","sequence":"additional","affiliation":[{"name":"IBM Research"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv:2312.11805"},{"key":"ref2","article-title":"Mini-omni: Language models can hear, talk while thinking in streaming","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv:2408.16725"},{"key":"ref3","article-title":"On the landscape of spoken language models: A comprehensive survey","author":"Arora","year":"2025","journal-title":"arXiv preprint arXiv:2504.08528"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref5","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras","author":"Abouelenin","year":"2025"},{"key":"ref6","article-title":"An embarrassingly simple approach for 11 m with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref7","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref8","article-title":"Qwen2-audio technical report","volume-title":"arXiv preprint arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3588378"},{"key":"ref11","article-title":"Granite 3.0 language models","author":"Granite Team","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref14","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref17","first-page":"1","article-title":"The ami meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389689"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"key":"ref20","first-page":"517","article-title":"Switchboard: Telephone speech corpus for research and development","volume-title":"ieee","volume":"1","author":"Godfrey"},{"key":"ref21","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume":"4","author":"Cieri","year":"2004","journal-title":"LREC"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804303"},{"key":"ref23","first-page":"125","article-title":"Ted-lium: an automatic speech recognition dedicated corpus","author":"Rousseau","year":"2012","journal-title":"LREC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning.","author":"Li"},{"key":"ref30","article-title":"Ctrl: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019","journal-title":"arXiv preprint arXiv:1909.05858"},{"key":"ref31","first-page":"38 462","article-title":"Efficient sequence transduction by jointly predicting tokens and durations","volume-title":"International Conference on Machine Learning.","author":"Xu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref33","article-title":"Phi-4 technical report","volume-title":"arXiv preprint arXiv:2412.08905","author":"Abdin","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2940"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"ref38","article-title":"Unveiling safety vulnerabilities of large language models","author":"Kour","year":"2023","journal-title":"arXiv preprint arXiv:2311.04124"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.234"}],"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\/11434651.pdf?arnumber=11434651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:49Z","timestamp":1775192269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434651","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}