{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:29:19Z","timestamp":1777390159252,"version":"3.51.4"},"reference-count":32,"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\/icassp49660.2025.10888331","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":1,"title":["Injecting Visual Features into Whisper for Parameter-Efficient Noise-Robust Audio-Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue Heng","family":"Yeo","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Jiang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiguang","family":"Chen","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xi","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref4","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi"},{"key":"ref5","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Haliassos"},{"key":"ref6","first-page":"21157","article-title":"u-hubert: Unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality","volume":"35","author":"Hsu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-387"},{"key":"ref13","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref14","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref15","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.308"},{"key":"ref18","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref19","article-title":"Audio-visual fine-tuning of audio-only asr models","author":"May","year":"2023"},{"key":"ref20","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448047"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02195"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"ref28","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref29","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref32","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"}],"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\/10888331.pdf?arnumber=10888331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:54Z","timestamp":1774416174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888331","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}