{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:03Z","timestamp":1775229903717,"version":"3.50.1"},"reference-count":45,"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\/icassp49660.2025.10890590","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation"],"prefix":"10.1109","author":[{"given":"Siyin","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University"}]},{"given":"Wenyi","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yudong","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Changli","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Jimin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Xianzhao","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Xiaohai","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Guangzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Cambridge"}]},{"given":"Lu","family":"Lu","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","volume-title":"Proc. NIPS End-to-end Learning for Speech and Audio Processing Workshop","author":"Patton"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-646"},{"key":"ref7","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref8","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. ICLR","author":"Tang"},{"key":"ref9","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref11","article-title":"Qwen2-Audio technical report","author":"Chu","year":"2024"},{"key":"ref12","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref16","article-title":"BAT: Learning to reason about spatial sounds with large language models","volume-title":"Proc. ICML","author":"Zheng"},{"key":"ref17","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref18","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446343"},{"key":"ref20","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1306"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2419"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34548"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.218"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1508"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-325"},{"key":"ref32","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref35","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref36","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"issue":"3","key":"ref37","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref38","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref39","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/pcs.2013.6737772"},{"key":"ref44","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096255"}],"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\/10890590.pdf?arnumber=10890590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:29Z","timestamp":1774416209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890590","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}