{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:10:19Z","timestamp":1782403819865,"version":"3.54.5"},"reference-count":29,"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\/icassp40776.2020.9053205","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6879-6883","source":"Crossref","is-referenced-by-count":86,"title":["Specaugment on Large Scale Datasets"],"prefix":"10.1109","author":[{"given":"Daniel S.","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youzheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quoc V.","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"hannun","year":"2014","journal-title":"Deep speech Scaling up end-to-end speech recognition"},{"key":"ref11","article-title":"Audio Augmentation for Speech Recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"ref13","author":"raju","year":"2018","journal-title":"Data Augmentation for Robust Keyword Spotting under Playback Interference"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472765"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.09.023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_71"},{"key":"ref18","article-title":"Learning the SpeechFront-end With Raw Waveform CLDNNs","author":"sainath","year":"2015","journal-title":"InterSpeech"},{"key":"ref19","article-title":"Acoustic Modeling for Google Home","author":"li","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref29","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","article-title":"Vocal Tract Length Perturbation (VTLP) improves speech recogni-tion","author":"jaitly","year":"2013","journal-title":"ICML Workshop on Deep Learning for Audio Speech and Language Processing"},{"key":"ref7","article-title":"Data augmentation for low resource languages","author":"ragni","year":"2014","journal-title":"InterSpeech"},{"key":"ref2","article-title":"Toward domain-invariant speech recognition via large scale training","author":"narayanan","year":"2018","journal-title":"ArXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3227"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref22","author":"gulcehre","year":"2015","journal-title":"On using monolingual corpora in neural machine translation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-40"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"InterSpeech"},{"key":"ref26","author":"han","year":"2019","journal-title":"State-of-the-art speech recognition using multi-stream self-attention with dilated 1d convolutions"},{"key":"ref25","author":"karita","year":"2019","journal-title":"A comprative study on Transformer vs RNN in speech applications"}],"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\/09053205.pdf?arnumber=9053205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:33Z","timestamp":1656375573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053205","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}