{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T19:29:43Z","timestamp":1793820583484,"version":"4.6.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414483","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7008-7012","source":"Crossref","is-referenced-by-count":67,"title":["MixSpeech: Data Augmentation for Low-Resource Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Linghui","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jindong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref13","article-title":"Semantic mask for transformer based end-to-end speech recognition","author":"wang","year":"2019"},{"key":"ref14","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"ref17","article-title":"Augmenting data with mixup for sentence classification: An empirical study","author":"guo","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref28","first-page":"4041","article-title":"A minimum-mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition","author":"yu","year":"2008","journal-title":"2008 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(00)00308-8"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-6","article-title":"Recurrent neural networks for noise reduction in robust asr","author":"maas","year":"2012"},{"key":"ref5","article-title":"Transformers with convolutional context for asr","author":"mohamed","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1020"},{"key":"ref7","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_71"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref24","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177697196"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1007\/11939993_73","article-title":"Hkust\/mts: A very large scale mandarin telephone speech corpus","author":"liu","year":"2006","journal-title":"International Symposium on Chinese Spoken Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414483.pdf?arnumber=9414483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:23:43Z","timestamp":1672129423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414483","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}