{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:17Z","timestamp":1775230157307,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639610","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"441-447","source":"Crossref","is-referenced-by-count":60,"title":["Toward Domain-Invariant Speech Recognition via Large Scale Training"],"prefix":"10.1109","author":[{"given":"Arun","family":"Narayanan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananya","family":"Misra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Golan","family":"Pundak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anshuman","family":"Tripathi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elfeky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parisa","family":"Haghani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Generalizing across domains via crossgradient training","author":"shankar","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268938"},{"key":"ref33","author":"valin","year":"2012","journal-title":"Definition of the Opus Audio Codec"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2246"},{"key":"ref35","year":"0","journal-title":"SBC library"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2010.5735742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"404","DOI":"10.21437\/Interspeech.2017-398","article-title":"On multidomain training and adaptation of end-to-end rnn acoustic models for distant speech recognition","author":"mirsamadi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref13","first-page":"588","article-title":"An experimental study on joint modeling of mixed-bandwidth data via deep neural networks for robust speech recognition","author":"gao","year":"2016","journal-title":"Neural Networks (IJCNN) 2016 International Joint Conference on"},{"key":"ref14","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","author":"bengio","year":"2012","journal-title":"Proc ICML Workshop Unsupervised Transfer Learn"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1109\/ICASSP.1992.225858","article-title":"Switchboard: Telephone speech corpus for research and development","volume":"1","author":"godfrey","year":"1992","journal-title":"Acoustics Speech and Signal Processing 1992 ICASSP-92 1992 IEEE International Conference on"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref17","first-page":"100","article-title":"The ami meeting corpus","volume":"88","author":"mccowan","year":"2005","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref18","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref29","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"arXiv preprint arXiv 1610 09975"},{"key":"ref5","article-title":"Feature learning in deep neural networks - studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref7","article-title":"Investigation of transfer learning for ASR using LFMMI trained neural networks","author":"ghahremani","year":"2017","journal-title":"Proc ASRU"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1544"},{"key":"ref20","article-title":"MP3 and AAC explained","author":"brandenburg","year":"1999","journal-title":"Audio Engineering Society Conference 17th International Conference High-Quality Audio Coding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref21","article-title":"FFmpeg","year":"0"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-249","article-title":"Bayesian language model interpolation for mobile speech input","author":"allauzen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1284"},{"key":"ref25","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639610.pdf?arnumber=8639610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:14:34Z","timestamp":1694625274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639610","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}