{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:48:26Z","timestamp":1776887306451,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003844","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"222-229","source":"Crossref","is-referenced-by-count":16,"title":["Speaker-Aware Speech-Transformer"],"prefix":"10.1109","author":[{"given":"Zhiyun","family":"Fan","sequence":"first","affiliation":[]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shiyu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Technical Report of IEICE Signal Processing Society"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref11","article-title":"The speechtransformer for large-scale mandarin chinese speech recognition","author":"wang","year":"2019","journal-title":"2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref13","first-page":"791","article-title":"Syllable-based sequence-to-sequence speech recognition with the transformer in mandarin chinese","author":"shiyu","year":"2018","journal-title":"Interspeech 2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref17","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref19","article-title":"Embedding-based speaker adaptive training of deep neural networks","volume":"abs 1710 6937","author":"cui","year":"2017","journal-title":"CoRR"},{"key":"ref28","article-title":"AISHELL-2: transforming mandarin ASR research into industrial scale","volume":"abs 1808 10583","author":"du","year":"2018","journal-title":"CoRR"},{"key":"ref4","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref3","author":"cho","year":"2014","journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref8","author":"graves","year":"2012","journal-title":"Sequence transduction with recurrent neural networks"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Speaker adaptation for end-to-end CTC models","volume":"abs 1901 1239","author":"li","year":"2019","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref24","article-title":"Evaluation of feature-space speaker adaptation for end-to-end acoustic models","author":"tomashenko","year":"2018","journal-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659609"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003844.pdf?arnumber=9003844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:49:25Z","timestamp":1658141365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003844","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}