{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:39Z","timestamp":1775229939115,"version":"3.50.1"},"reference-count":39,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888128","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":2,"title":["MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders"],"prefix":"10.1109","author":[{"given":"Wenyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunlong","family":"Zou","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuohan","family":"Liu","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxu","family":"He","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ai","family":"Ti Aw","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Hugo Touvron","year":"2023","journal-title":"arXiv"},{"key":"ref3","author":"Wei-Lin Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref4","article-title":"SALMONN: Towards generic hearing abilities for large language models","author":"Changli Tang","year":"2024","journal-title":"ICLR"},{"key":"ref5","article-title":"Qwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Yunfei Chu","year":"2023","journal-title":"arXiv"},{"key":"ref6","article-title":"Pengi: An audio language model for audio tasks","author":"Soham Deshmukh","year":"2023","journal-title":"NeurIPS"},{"key":"ref7","article-title":"WavLLM: Towards robust and adaptive speech large language model","author":"Shujie Hu","year":"2023","journal-title":"arXiv"},{"key":"ref8","article-title":"SpeechVerse: A large-scale generalizable audio language model","author":"Nilaksh Das","year":"2024","journal-title":"arXiv"},{"key":"ref9","author":"Haotian Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref10","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Wenliang Dai","year":"2024","journal-title":"NeurIPS"},{"key":"ref11","article-title":"MERaLiON-AudioLLM: Bridging audio and language with large language models","year":"2024","journal-title":"arXiv"},{"key":"ref12","article-title":"Advancing Singlish understanding: Bridging the gap with datasets and multimodal models","author":"Bin Wang","year":"2025","journal-title":"arXiv"},{"key":"ref13","article-title":"VioLA: Unified codec language models for speech recognition, synthesis, and translation","author":"Tianrui Wang","year":"2023","journal-title":"arXiv"},{"key":"ref14","article-title":"LLaSM: Large language and speech model","author":"Yu Shu","year":"2023","journal-title":"arXiv"},{"key":"ref15","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Paul","year":"2023","journal-title":"arXiv"},{"key":"ref16","article-title":"Audio Flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Zhifeng Kong","year":"2024","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"ref18","article-title":"Robust speech recognition via large-scale weak supervision","author":"Alec Radford","year":"2023","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Sanyuan Chen","year":"2023","journal-title":"ICML"},{"key":"ref22","volume-title":"Hubert-base for emotion recognition","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref24","article-title":"Qwen technical report","author":"Jinze Bai","year":"2023","journal-title":"arXiv"},{"key":"ref25","article-title":"Mixtral of experts","author":"Albert","year":"2024","journal-title":"arXiv"},{"key":"ref26","article-title":"LoRA: Low-rank adaptation of large language models","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref27","article-title":"Mixture of LoRA experts","author":"Xun Wu","year":"2024","journal-title":"ICLR"},{"key":"ref28","article-title":"A survey on mixture of experts","author":"Weilin Cai","year":"2024","journal-title":"arXiv"},{"key":"ref29","article-title":"MoVA: Adapting mixture of vision experts to multimodal context","author":"Zhuofan Zong","year":"2024","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco55093.2022.9909680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1714"},{"key":"ref34","article-title":"AudioCaps: Generating captions for audios in the wild","author":"Chris Dongjoo Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref35","article-title":"Audiobench: A universal benchmark for audio large language models","author":"Bin Wang","year":"2024","journal-title":"arXiv"},{"key":"ref36","year":"2024","journal-title":"Llama 3 model card"},{"key":"ref37","article-title":"Zephyr: Direct distillation of LM alignment","author":"Lewis Tunstall","year":"2023","journal-title":"arXiv"},{"key":"ref38","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Marah Abdin","year":"2024","journal-title":"arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"}],"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\/10888128.pdf?arnumber=10888128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:08Z","timestamp":1774416368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888128","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}