{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T12:34:16Z","timestamp":1790771656438,"version":"4.1.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414182","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"316-320","source":"Crossref","is-referenced-by-count":15,"title":["An End-To-End Non-Intrusive Model for Subjective and Objective Real-World Speech Assessment Using a Multi-Task Framework"],"prefix":"10.1109","author":[{"given":"Zhuohuang","family":"Zhang","sequence":"first","affiliation":[{"name":"Indiana University,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piyush","family":"Vyas","sequence":"additional","affiliation":[{"name":"Indiana University,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Dong","sequence":"additional","affiliation":[{"name":"Indiana University,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donald S.","family":"Williamson","sequence":"additional","affiliation":[{"name":"Indiana University,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref31","first-page":"136","article-title":"A hierarchical bayesian approach to modeling heterogeneity in speech quality assessment","volume":"20","author":"mossavat","year":"2011","journal-title":"TASLP"},{"key":"ref30","article-title":"An overview of multi-task learning in deep neural networks","author":"ruder","year":"2017"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref11","first-page":"821","article-title":"ANIQUE: An auditory model for single-ended speech quality estimation","volume":"13","author":"kim","year":"2005","journal-title":"tsap"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953125"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683770"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109381"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760550"},{"key":"ref17","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"2016","journal-title":"NeurIPS Workshop on End-to-end Learning for Speech and Audio Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref28","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"96","author":"ester","year":"1996","journal-title":"KDD"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref27","author":"han","year":"2011","journal-title":"Data Mining Concepts and Techniques"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref7","first-page":"366","article-title":"Perceptual objective listening quality assessment (POLQA), the third generation itut standard for end-to-end speech quality measurement part i—temporal alignment","volume":"61","author":"beerends","year":"2013","journal-title":"J Aud Eng Soc"},{"key":"ref2","article-title":"ADL-MVDR: All deep learning MVDR beamformer for target speech separation","author":"zhang","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177963"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2809"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1481"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053366"},{"key":"ref26","article-title":"BS. 1534 method for the subjective assessment of intermediate quality level of audio systems","year":"2014","journal-title":"ITU Recommendation"},{"key":"ref25","first-page":"4153","article-title":"COSINE-a corpus of multiparty conversational speech in noisy environments","author":"stupakov","year":"2009","journal-title":"ICASSP"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414182.pdf?arnumber=9414182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:39Z","timestamp":1659486039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414182","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}