{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T21:06:43Z","timestamp":1777583203032,"version":"3.51.4"},"reference-count":37,"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\/icassp49357.2023.10094705","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":17,"title":["Self-Supervised Learning for Speech Enhancement Through Synthesis"],"prefix":"10.1109","author":[{"given":"Bryce","family":"Irvin","sequence":"first","affiliation":[{"name":"Bose Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marko","family":"Stamenovic","sequence":"additional","affiliation":[{"name":"Bose Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikolaj","family":"Kegler","sequence":"additional","affiliation":[{"name":"Bose Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Chia","family":"Yang","sequence":"additional","affiliation":[{"name":"Bose Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref35","article-title":"P.808 : Subjective evaluation of speech quality with a crowdsourcing approach","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747348"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013699998"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref36","first-page":"25","article-title":"Byol-s: Learning self-supervised speech representations by bootstrapping","author":"elbanna","year":"2022","journal-title":"HEAR Holistic Evaluation of Audio Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref30","article-title":"P.862 : Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10498"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","article-title":"Evaluation of objective quality measures for speech enhancement","volume":"16","author":"hu","year":"2008","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1864"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref17","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","author":"choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206623"},{"key":"ref19","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"ArXiv"},{"key":"ref24","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref26","article-title":"ITU-R BS.1770-4: Algorithms to measure audio programme loudness and true-peak audio level","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414853"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref27","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"valentini-botinhao","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003785"},{"key":"ref3","article-title":"Weight, block or unitƒ exploring sparsity tradeoffs for speech enhancement on tiny neural accelerators","author":"stamenovic","year":"2021","journal-title":"NeurIPS ENLSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"}],"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\/10094705.pdf?arnumber=10094705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:01:56Z","timestamp":1700488916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094705","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}