{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T23:22:21Z","timestamp":1725751341914},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428334","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T17:14:21Z","timestamp":1623258861000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jian","family":"Luo","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}]},{"given":"Edward","family":"Xiao","sequence":"additional","affiliation":[{"name":"Aquinas International Academy,CA,USA"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}]},{"given":"Georg","family":"Kucsko","sequence":"additional","affiliation":[{"name":"Kensho,Cambridge,MA,USA"}]},{"given":"Patrick","family":"O'Neill","sequence":"additional","affiliation":[{"name":"Kensho,Cambridge,MA,USA"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Slyne","family":"Deng","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Adriana","family":"Flores","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Jocelyn","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Oleksii","family":"Kuchaiev","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Vitaly","family":"Lavrukhin","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Jason","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]}],"member":"263","reference":[{"journal-title":"arXiv 1905 11286","article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","year":"2019","author":"ginsburg","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"journal-title":"INTER-SPEECH","article-title":"Large-scale transfer learning for low-resource spoken language understanding","year":"2020","author":"jia","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2620"},{"journal-title":"arXiv 1712 09444","article-title":"Letter-based speech recognition with gated convnets","year":"2017","author":"liptchinsky","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.03.179"},{"journal-title":"Speech Communication","article-title":"Multilingual training and cross-lingual adaptation on CTC-based acoustic model","year":"2017","author":"tong","key":"ref16"},{"journal-title":"arXiv 1911 09271","article-title":"Cantonese automatic speech recognition using transfer learning from mandarin","year":"2019","author":"li","key":"ref17"},{"journal-title":"arXiv 1808 10583","article-title":"AISHELL-2: Transforming mandarin asr research into industrial scale","year":"2018","author":"du","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"journal-title":"LREC","article-title":"The Fisher corpus: a resource for the next generations of speech-to-text","year":"2004","author":"cieri","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","author":"mccloskey","year":"1989","journal-title":"Psychology of Learning and Motivation - Advances in Research and Theory"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"journal-title":"Switchboard-1 Release 2 LDC97S62","year":"1993","author":"godfrey","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389340"},{"journal-title":"arXiv 1909 09577","article-title":"Nemo: a toolkit for building AI applications using neural modules","year":"2019","author":"kuchaiev","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00094-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"article-title":"IARPA Babel Cantonese language pack IARPA-babel101b-v0.4c, LDC97S62","year":"2016","author":"andrus","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"journal-title":"The Corpus of Regional African American Language","year":"2018","author":"kendall","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1525"},{"journal-title":"arXiv 1912 06670","article-title":"Common Voice: A massively-multilingual speech corpus","year":"2019","author":"ardila","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428334.pdf?arnumber=9428334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T17:27:44Z","timestamp":1656350864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428334","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}
