{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:55:36Z","timestamp":1783526136318,"version":"3.55.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414087","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6778-6782","source":"Crossref","is-referenced-by-count":19,"title":["Transformer in Action: A Comparative Study of Transformer-Based Acoustic Models for Large Scale Speech Recognition Applications"],"prefix":"10.1109","author":[{"given":"Yongqiang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Feng","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Improving RNN transducer based ASR with auxiliary tasks","author":"liu","year":"2021","journal-title":"Submitted to SLT IEEE Workshop on Spoken Language Technology"},{"key":"ref32","article-title":"Benchmarking LF-MMI, CTC and RNN-T criteria for streaming ASR","author":"zhang","year":"2021","journal-title":"Submitted to SLT IEEE Workshop on Spoken Language Technology"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref34","article-title":"Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition","author":"yeh","year":"2021","journal-title":"Submitted to SLT IEEE Workshop on Spoken Language Technology"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref16","article-title":"Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory","author":"wu","year":"2020"},{"key":"ref17","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref18","volume":"247","author":"bourlard","year":"0","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225979"},{"key":"ref28","article-title":"faster, simpler and more accurate hybrid asr systems using wordpieces","year":"0"},{"key":"ref4","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref3","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref8","article-title":"Feedforward sequential memory neural networks without recurrent feedback","author":"zhang","year":"2015"},{"key":"ref7","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref1","article-title":"Emformer: efficient low latency streaming transformer acoustic model for speech recognition","author":"shi","year":"2021","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref26","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref25","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414087.pdf?arnumber=9414087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:41:02Z","timestamp":1652182862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414087","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}