{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:50Z","timestamp":1776956450611,"version":"3.51.4"},"reference-count":38,"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\/icassp49357.2023.10096390","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":15,"title":["LA-VOCE: LOW-SNR Audio-Visual Speech Enhancement Using Neural Vocoders"],"prefix":"10.1109","author":[{"given":"Rodrigo","family":"Mira","sequence":"first","affiliation":[{"name":"iBUG, Imperial College London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob","family":"Donley","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"iBUG, Imperial College London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vamsi Krishna","family":"Ithapu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"iBUG, Imperial College London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref35","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref34","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2991537"},{"key":"ref37","author":"yamagishi","year":"2012","journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref14","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"ICLRE"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref16","first-page":"2452","article-title":"Noise tokens: Learning neural noise templates for environment-aware speech enhancement","author":"li","year":"2020","journal-title":"InterSpeech"},{"key":"ref38","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref23","first-page":"2978","author":"dai","year":"2019","journal-title":"Transformer-xl Attentive language models beyond a fixed-length context"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref25","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume":"48","author":"larsen","year":"0"},{"key":"ref20","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref7","first-page":"1170","article-title":"Visual speech enhancement","author":"gabbay","year":"2018","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref4","first-page":"1786","article-title":"UNetGAN: A robust speech enhancement approach in time domain for extremely low signal-to-noise ratio condition","author":"hao","year":"2019","journal-title":"InterSpeech"},{"key":"ref3","first-page":"3291","article-title":"Real time speech enhancement in the waveform domain","author":"d\u00e9fossez","year":"2020","journal-title":"InterSpeech"},{"key":"ref6","first-page":"1836","article-title":"SVTS: scalable video-to-speech synthesis","author":"mira","year":"2022","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162495"}],"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\/10096390.pdf?arnumber=10096390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:10:10Z","timestamp":1700507410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096390","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}