{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:02:30Z","timestamp":1776880950477,"version":"3.51.2"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447687","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"376-380","source":"Crossref","is-referenced-by-count":4,"title":["Corn: Co-Trained Full- and No-Reference Speech Quality Assessment"],"prefix":"10.1109","author":[{"given":"Pranay","family":"Manocha","sequence":"first","affiliation":[{"name":"Princeton University,Department of Computer Science,Princeton,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donald","family":"Williamson","sequence":"additional","affiliation":[{"name":"The Ohio State University,Department of Computer Science and Engineering,Columbus,OH,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Finkelstein","sequence":"additional","affiliation":[{"name":"Princeton University,Department of Computer Science,Princeton,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref2","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)","volume-title":"ICASSP","volume":"2","author":"Rix"},{"key":"ref3","article-title":"Perceptual objective listening quality assessment (POLQA)","author":"Beerends","year":"2013","journal-title":"Journal of the AES"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953337"},{"key":"ref10","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","volume-title":"ICASSP","author":"Reddy"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-659"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414182"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054204"},{"key":"ref18","article-title":"NORESQA: A framework for speech quality assessment using non-matching references","volume":"34","author":"Manocha","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00495"},{"key":"ref22","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"ICML","author":"Fu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414052"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2174223"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032266"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2847459"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref28","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"Patton","year":"2016"},{"key":"ref29","first-page":"5447","article-title":"A sequential self teaching approach for improving generalization in sound event recognition","volume-title":"ICML","author":"Kumar"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.838101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.02.023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.84.4.327"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414052"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3205757"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref38","first-page":"2725","article-title":"An evaluation of synthetic speech using the PESQ measure","volume-title":"Proc. European Congress on Acoustics","author":"Cernak"},{"key":"ref39","article-title":"Measurement of speech intelligibility based on the pesq approach","volume-title":"MESAQIN","author":"Beerends"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AMUEM.2007.4362580"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2014.2379648"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"key":"ref43","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"Garofolo","year":"1993","journal-title":"NASA Technical Report"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447687.pdf?arnumber=10447687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:34:38Z","timestamp":1722573278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447687","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}