{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:37:35Z","timestamp":1776530255226,"version":"3.51.2"},"reference-count":29,"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\/icassp43922.2022.9747463","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6947-6951","source":"Crossref","is-referenced-by-count":10,"title":["Continual Self-Training With Bootstrapped Remixing For Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Efthymios","family":"Tzinis","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Meta AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vamsi K.","family":"Ithapu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682695"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413723"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","article-title":"Fsd50k: an open dataset of human-labeled sound events","author":"fonseca","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688176"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"ref6","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","author":"wisdom","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref29","first-page":"749","article-title":"Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs","author":"rix","year":"2001","journal-title":"Proc ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1868"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632783"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616166"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref9","article-title":"Training speech enhancement systems with noisy speech datasets","author":"saito","year":"2021"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref21","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref26","first-page":"626","article-title":"Sdr–half-baked or well done?","author":"roux","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref25","article-title":"Compute and memory efficient universal sound source separation","author":"tzinis","year":"2021","journal-title":"Journal of Signal Processing Systems"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09747463.pdf?arnumber=9747463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:14Z","timestamp":1660593974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747463","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}