{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:04:26Z","timestamp":1751094266597,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746615","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"891-895","source":"Crossref","is-referenced-by-count":4,"title":["SQAPP: No-Reference Speech Quality Assessment Via Pairwise Preference"],"prefix":"10.1109","author":[{"given":"Pranay","family":"Manocha","sequence":"first","affiliation":[{"name":"Princeton University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Finkelstein","sequence":"additional","affiliation":[{"name":"Princeton University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref38","first-page":"1632","article-title":"The Voice Conversion Challenge 2016","author":"toda","year":"2016","journal-title":"InterSpeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683654"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109381"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref37","article-title":"Spatial audio object coding (SAOC)-the upcoming mpeg standard on parametric object based audio coding","author":"breebaart","year":"2008","journal-title":"AES Convention 124"},{"key":"ref36","article-title":"Evaluating physical measures for predicting the perceived quality of blindly separated audio source signals","author":"kastner","year":"2009","journal-title":"AES Convention"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2015.7148100"},{"key":"ref10","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"reddy","year":"2020","journal-title":"ICASSP"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2847459"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414182"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref19","article-title":"NORESQA: A framework for speech quality assessment using non-matching references","volume":"34","author":"manocha","year":"0","journal-title":"NeurIPS 2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref27","article-title":"FSD50k: an open dataset of human-labeled sound events","author":"fonseca","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref6","article-title":"Can we automatically transform speech recorded on common consumer devices in real-world environments into professional production quality speech?—a dataset, insights, and challenges","volume":"22","author":"mysore","year":"2014","journal-title":"IEEE SPSN"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073702"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","year":"2017","author":"valentini-botinhao","key":"ref7"},{"key":"ref2","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","author":"beerends","year":"2013","journal-title":"Journal of the AES"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953337"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0070288"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-015-0858-8"},{"key":"ref42","article-title":"The interspeech 2020 deep noise suppression challenge: Datasets, subjective speech quality and testing framework","author":"reddy","year":"0","journal-title":"Interspeech 2020"},{"key":"ref24","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018","journal-title":"arXiv preprint arXiv 1803 01271"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref25","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746615.pdf?arnumber=9746615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:16Z","timestamp":1660594216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746615","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}