{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:28:12Z","timestamp":1776889692374,"version":"3.51.2"},"reference-count":43,"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\/asru65441.2025.11434623","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":20,"title":["Meta Audiobox Aesthetics: Unified Automatic Assessment for Speech, Music and Sound"],"prefix":"10.1109","author":[{"given":"Andros","family":"Tjandra","sequence":"first","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Baishan","family":"Guo","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"John","family":"Hoffman","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Brian","family":"Ellis","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Apoorv","family":"Vyas","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Bowen","family":"Shi","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Sanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Matt","family":"Le","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Nick","family":"Zacharov","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Carleigh","family":"Wood","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Ann","family":"Lee","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"FAIR at Meta, Reality Labs at Meta,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"1401: Methods, metrics and procedures for statistical evaluation, qualification and comparison of objective quality prediction models","year":"2001","journal-title":"International Telecommunications Union-Radiocommunication"},{"key":"ref2","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref3","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)","author":"Ardila"},{"key":"ref4","article-title":"Layer normalization","volume":"1","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"issue":"6","key":"ref5","first-page":"366","article-title":"Perceptual objective listening quality assessment (polqa), the third generation itu-t standard for end-to-end speech quality measurement part i-temporal alignment","volume":"61","author":"Beerends","year":"2013","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-325"},{"key":"ref12","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref16","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint arXiv:1606.08415"},{"key":"ref17","article-title":"Mos-bench: Benchmarking generalization abilities of subjective speech quality assessment models","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv:2411.03715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612140"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref22","article-title":"Frechet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018","journal-title":"arXiv preprint arXiv:1812.08466"},{"key":"ref23","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics","volume":"1","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref25","article-title":"Laion-aesthetics","journal-title":"LAION"},{"key":"ref26","article-title":"The llama 3 herd of models","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/info14070358"},{"key":"ref31","article-title":"Automos: Learning a non-intrusive assessor of naturalness-of-speech","author":"Patton","year":"2016","journal-title":"arXiv preprint arXiv:1611.09207"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389788"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Stylianos Ioannis Mimilakis, and Rachel Bittner","author":"Rafii","year":"2019","journal-title":"Musdb18-hq - an uncompressed version of musdb18"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv preprint arXiv:2312.15821"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2019-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"}],"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\/11434623.pdf?arnumber=11434623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:21Z","timestamp":1775192241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434623","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}