{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:00:48Z","timestamp":1776445248800,"version":"3.51.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848913","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Generalized SpecAugment: Robust Online Augmentation Technique for End-to-End Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Meet","family":"Soni","sequence":"first","affiliation":[{"name":"Rakuten Institute of Technology,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Panda","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil Kumar","family":"Kopparapu","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","volume-title":"Proc. ICML Workshop on Deep Learning for Audio, Speech and Language","volume":"117","author":"Jaitly"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref3","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref4","first-page":"46","article-title":"Multilingual graphemic hybrid asr with massive data augmentation","volume-title":"Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)","author":"Liu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SSD.2019.8893184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682816"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472765"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.09.023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_71"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383626"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2275"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"issue":"EPFL-CONF-192584","key":"ref23","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-139"},{"key":"ref26","article-title":"TED-LIUM: an automatic speech recognition dedicated corpus","volume-title":"Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912)","author":"Rousseau"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848913.pdf?arnumber=10848913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:03Z","timestamp":1738045383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848913","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}