{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:06:10Z","timestamp":1781798770953,"version":"3.54.5"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096680","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":53,"title":["Torchaudio-Squim: Reference-Less Speech Quality and Intelligibility Measures in Torchaudio"],"prefix":"10.1109","author":[{"given":"Anurag","family":"Kumar","sequence":"first","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Tan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranay","family":"Manocha","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan","family":"Henderson","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"911","article-title":"An attention enhanced multi-task model for objective speech assessment in real-world environments","author":"dong","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref15","first-page":"482","article-title":"Stoi-net: A deep learning based non-intrusive speech intelligibility assessment model","author":"zezario","year":"2020","journal-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref14","article-title":"A classification-aided frame-work for non-intrusive speech quality assessment","author":"dong","year":"2019","journal-title":"WAS-PAA"},{"key":"ref30","first-page":"380","article-title":"Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement","volume":"28","author":"tan","year":"2019","journal-title":"IEEE\/ACM TASLP"},{"key":"ref11","first-page":"316","article-title":"An end-to-end non-intrusive model for subjective and objective real-world speech assessment using a multi-task framework","author":"zhang","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054204"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:20000539"},{"key":"ref1","article-title":"Speech quality assessment","author":"loizou","year":"2011","journal-title":"Multimedia analysis and communications"},{"key":"ref17","article-title":"Deep learning-based non-intrusive multi-objective speech assessment model with cross-domain features","author":"zezario","year":"2022","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-659"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref24","article-title":"NORESQA: A framework for speech quality assessment using non-matching references","volume":"34","author":"manocha","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-407"},{"key":"ref26","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref20","article-title":"P.862.2: Wideband extension to recommendation P.862 for the assessment of wideband telephone networks and speech codecs","author":"rec","year":"2005","journal-title":"International Telecommunication Union Geneva"},{"key":"ref22","first-page":"626","article-title":"SDR– half-baked or well done?","author":"le roux","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref8","first-page":"896","article-title":"LD-Net: Unified listener dependent modeling in MOS prediction for synthetic speech","author":"huang","year":"2022","journal-title":"IEEE ICASSP IEEE"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref4","first-page":"1541","article-title":"MOSNet: Deep learning based ob-jective assessment for voice conversion","author":"lo","year":"2019","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref5","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"2016","journal-title":"NIPS 2016 End-to-end Learning for Speech and Audio Processing Workshop"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096680.pdf?arnumber=10096680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:02:28Z","timestamp":1700488948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096680","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}