{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:38Z","timestamp":1730199338028,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688002","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"989-995","source":"Crossref","is-referenced-by-count":1,"title":["A Comparison of Streaming Models and Data Augmentation Methods for Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jiyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Mehul","family":"Kumar","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Abhinav","family":"Garg","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3174"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","first-page":"379","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":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref13","article-title":"Specaugment on large scale datasets","volume":"abs 1912 5533","author":"park","year":"2019","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3227"},{"key":"ref15","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","author":"jaitly","year":"0","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref17","article-title":"Advances in joint ctc-attention based end-to-end speech recognition with a deep cnn encoder and rnn-lm","author":"hori","year":"0","journal-title":"InterSpeech"},{"key":"ref18","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"0","journal-title":"ICML"},{"key":"ref19","article-title":"Monotonic chunkwise attention","author":"chiu","year":"0","journal-title":"ICLRE"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3230"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","volume":"abs 2003 12710","author":"sainath","year":"2020","journal-title":"A streaming on-device end-to-end model surpassing server-side conventional model quality and latency"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443456"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref22","article-title":"Sequence to sequence transduction with hard monotonic attention","volume":"abs 1611 1487","author":"aharoni","year":"2016","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003976"},{"key":"ref24","article-title":"Acoustic modeling for Google Home","author":"li","year":"0","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2566"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003973"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178831"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688002.pdf?arnumber=9688002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:19Z","timestamp":1652719339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688002","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}