{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T08:28:21Z","timestamp":1788164901687,"version":"build-2803163510"},"reference-count":27,"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\/icassp49660.2025.10889566","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":3,"title":["Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Simic","sequence":"first","affiliation":[{"name":"Technische Hochschule Nuernberg,Nuernberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nuernberg,Nuernberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nuernberg,Nuernberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095430"},{"key":"ref3","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS\u201920","author":"Baevski"},{"key":"ref4","article-title":"Octavius: Mitigating Task Interference in MLLMs via MoE","volume-title":"2024 International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref10","article-title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","volume-title":"2023 International Conference on Learning Representations (ICLR)","author":"Haliassos"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"2022 International Conference on Learning Representations (ICLR)","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref17","article-title":"Audio-visual fine-tuning of audio-only ASR models","author":"May","year":"2023","journal-title":"CoRR"},{"key":"ref18","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"ICML","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02195"},{"key":"ref21","article-title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","volume-title":"2022 International Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448047"},{"key":"ref24","article-title":"MUSAN: A Music, Speech, and Noise Corpus, 2015","author":"Snyder"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446321"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref27","article-title":"Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhao"}],"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\/10889566.pdf?arnumber=10889566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:45Z","timestamp":1774416165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889566","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}