{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:20:49Z","timestamp":1753600849982,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054697","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7309-7313","source":"Crossref","is-referenced-by-count":3,"title":["An Analysis of Speech Enhancement and Recognition Losses in Limited Resources Multi-Talker Single Channel Audio-Visual ASR"],"prefix":"10.1109","author":[{"given":"Luca","family":"Pasa","sequence":"first","affiliation":[{"name":"Istituto Italiano di Tecnologia,Ferrara,Italy"}]},{"given":"Giovanni","family":"Morrone","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Department of Engineering \"Enzo Ferrari\",Modena,Italy"}]},{"given":"Leonardo","family":"Badino","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Ferrara,Italy"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"assael","year":"2017","journal-title":"GPU Technology Conference"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.21437\/Interspeech.2017-667","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref17","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref19","first-page":"8077","article-title":"On training targets and objective functions for deep-learning-based audiovisual speech enhancement","author":"michelsanti","year":"2019","journal-title":"2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2372314"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref3","article-title":"Joint training of speech separation, filter-bank and acoustic model for robust automatic speech recognition","author":"wang","year":"2015","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref5","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"2015","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014067"},{"key":"ref23","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820893"},{"key":"ref25","article-title":"A survey on multi-task learning","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1707 08114"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054697.pdf?arnumber=9054697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:12Z","timestamp":1659484632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054697","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}