{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:33:58Z","timestamp":1770226438365,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383518","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"873-880","source":"Crossref","is-referenced-by-count":14,"title":["RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions"],"prefix":"10.1109","author":[{"given":"Chung-Cheng","family":"Chiu","sequence":"first","affiliation":[]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Navdeep","family":"Jaitly","sequence":"additional","affiliation":[]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","article-title":"Acoustic modelling with cd-ctc-smbr lstm rnns","author":"senior","year":"2015","journal-title":"Proc of ASRU"},{"key":"ref31","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref14","first-page":"193","article-title":"Exploring Architectures, Data and Units for Streaming End-to-End Speech Recognition with RNN-Transducer","author":"rao","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref4","article-title":"Deep speech: Scaling Up End-to-End Speech Recognition","author":"hannun","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472823"},{"key":"ref3","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":"ref6","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.21437\/Interspeech.2017-1566","article-title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","author":"soltau","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref29","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Proc of NeurIPS"},{"key":"ref5","first-page":"173","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc of ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","first-page":"577","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1566"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383518.pdf?arnumber=9383518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:56Z","timestamp":1622496656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383518","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}