{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:58:33Z","timestamp":1775199513384,"version":"3.50.1"},"reference-count":28,"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\/asru65441.2025.11433844","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["MMMOS: Multi-domain Multi-axis Audio Quality Assessment"],"prefix":"10.1109","author":[{"given":"Yi-Cheng","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University"}]},{"given":"Jia-Hung","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205757"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24425\/ijet.2024.149549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3536156"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3139010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref11","first-page":"90","article-title":"The efficacy of self-supervised speech models for audio representations","author":"Wu","year":"2022","journal-title":"HEAR: Holistic Evaluation of Audio Representations."},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2025-747","article-title":"Distilling a speech and music encoder with task arithmetic","author":"Ritter-Gutierrez","year":"2025"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU65441.2025.11433848","article-title":"A correlation-permutation approach for speech-music encoders model merging","author":"Ritter-Gutierrez","year":"2025"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref18","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref19","article-title":"Musdb18-hq - an uncompressed version of musdb18","author":"Rafii","year":"2019"},{"key":"ref20","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3602320"},{"key":"ref23","article-title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation","author":"Niizumi","year":"2024","journal-title":"to appear at Interspeech"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"}],"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\/11433844.pdf?arnumber=11433844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:54:38Z","timestamp":1775192078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433844","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}