{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T18:22:18Z","timestamp":1777054938706,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icassp40776.2020.9053569","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6989-6993","source":"Crossref","is-referenced-by-count":160,"title":["Multi-Task Self-Supervised Learning for Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Mirco","family":"Ravanelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyuan","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santiago","family":"Pascual","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawel","family":"Swietojanski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joao","family":"Monteiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Trmal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-731"},{"key":"ref32","article-title":"DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus CDROM","author":"garofolo","year":"1993"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","article-title":"Rethinking learning rate schedules for stochastic optimization","author":"ge","year":"2019","journal-title":"openreview"},{"key":"ref37","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-775"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref34","article-title":"The fifth ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines","author":"vincent","year":"2018","journal-title":"Proc of Interspeech"},{"key":"ref10","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref16","article-title":"Quasi-Recurrent Neural Networks","author":"bradbury","year":"2017","journal-title":"Proc of ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404805"},{"key":"ref28","article-title":"Multi-objective training of generative adversarial networks with multiple discriminators","author":"albuquerque","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref4","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc of NIPS"},{"key":"ref27","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref3","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc of ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref7","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"Proc of ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref9","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref1","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2006","journal-title":"Proc of NIPS"},{"key":"ref20","article-title":"Contaminated speech training methods for robust DNN-HMM distant speech recognition","author":"ravanelli","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref22","article-title":"Interpretable convolutional filters with SincNet","author":"ravanelli","year":"2018","journal-title":"Proc of NIPS IRASL"},{"key":"ref21","article-title":"SpecAugment: A simple augmentation method for automatic speech recognition","author":"zoph","year":"2019","journal-title":"Proc of Interspeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref23","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc of ICML"},{"key":"ref26","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"Proc of ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366996"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"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\/09053569.pdf?arnumber=9053569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:58Z","timestamp":1656374938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053569","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}