{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:54:12Z","timestamp":1761648852327},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362086","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning"],"prefix":"10.1109","author":[{"given":"Zhiping","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Van Tung","family":"Pham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haihua","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yerbolat","family":"Khassanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjia","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multilingual training and cross-lingual adaptation on ctc-based acoustic model","author":"tong","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref12","first-page":"5884","article-title":"Speech-transformer: A norecurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc of ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref14","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1458"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1166"},{"key":"ref19","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref4","article-title":"On using monolingual corpora in neural machine translation","author":"g\u00fcl\u00e7ehre","year":"2015","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc of ICML"},{"key":"ref1","first-page":"7054","article-title":"Independent language model architecture for end-to- end asr","author":"pham","year":"2020","journal-title":"Proc of ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682850"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1525"},{"key":"ref22","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc of ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362086.pdf?arnumber=9362086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T22:23:06Z","timestamp":1620080586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362086","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}