{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:19:24Z","timestamp":1776881964239,"version":"3.51.2"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434660","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["The AudioMOS Challenge 2025"],"prefix":"10.1109","author":[{"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,China"}]},{"given":"Cheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Nankai University,China"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Andros","family":"Tjandra","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,China"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref6","first-page":"13916","article-title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","volume-title":"Proc. ICML","volume":"202","author":"Huang"},{"key":"ref7","article-title":"Evaluating generative audio systems and their metrics","volume-title":"Proc. ISMIR","author":"Vinay"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10714935"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU65441.2025.11434623","article-title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","author":"Tjandra","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-692"},{"key":"ref12","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref13","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref15","article-title":"Hi-Fi-CAPTAIN: High-fidelity and high-capacity conversational speech synthesis corpus developed by NICT","author":"Okamoto","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3366707"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU65441.2025.11434754","article-title":"Speech masking system based on spatially separated multiple TTS maskers with a compact circular loudspeaker array","volume-title":"Proc. ASRU","author":"Okamoto"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref20","article-title":"pyloudnorm: A simple yet flexible loudness meter in python","author":"Steinmetz","year":"2021","journal-title":"Audio Engineering Society Convention 150."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref26","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint arXiv:1606.08415"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref30","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv:2311.07919"},{"key":"ref31","first-page":"5178","article-title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","volume-title":"Proc. ICML","volume":"202","author":"Chen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref33","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2023","journal-title":"TMLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-246"},{"key":"ref35","article-title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","volume-title":"Proc. ICLR","author":"LI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3602320"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref38","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"ref39","article-title":"Qwen3 Technical Report","volume-title":"arXiv preprint arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref40","first-page":"28492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Proc. ICML","volume":"202","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"issue":"97","key":"ref42","first-page":"1","article-title":"Scaling Speech Technology to 1,000+ Languages","volume":"25","author":"Pratap","year":"2024","journal-title":"JMLR"},{"key":"ref43","first-page":"3807","article-title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","volume-title":"Proc. IJCAI","volume":"8","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref45","article-title":"KAN: Kolmogorov-Arnold networks","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref46","first-page":"10041","article-title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","volume-title":"Proc. ICML","volume":"235","author":"Dao"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3203907"},{"key":"ref48","article-title":"Kolmogorov-Arnold transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2409.10594"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-demo.19"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434660.pdf?arnumber=11434660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:51Z","timestamp":1775192271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434660","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}