{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:52:15Z","timestamp":1776181935600,"version":"3.50.1"},"reference-count":35,"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\/icassp49660.2025.10889444","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":["Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"],"prefix":"10.1109","author":[{"given":"Ke-Han","family":"Lu","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Chao-Han Huck","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref3","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref4","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref5","article-title":"Listen, think, and understand","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gong"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref7","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref8","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref9","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref10","article-title":"Blsp: Bootstrapping language-speech pre-training via behavior alignment of continuation writing","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/syndata4genai.2024-9"},{"key":"ref16","article-title":"Speechverse: A large-scale generalizable audio language model","author":"Das","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref19","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Rafailov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1070"},{"key":"ref22","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref23","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li"},{"key":"ref24","first-page":"5353","article-title":"Accentdb: A database of non-native english accents to assist neural speech recognition","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference","author":"Ahamad"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref28","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389718"},{"key":"ref32","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref34","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref35","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"}],"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\/10889444.pdf?arnumber=10889444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:17Z","timestamp":1774416377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889444","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}