{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:39Z","timestamp":1740100539587,"version":"3.37.3"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)","doi-asserted-by":"publisher","award":["414091002"],"award-info":[{"award-number":["414091002"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688298","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"177-184","source":"Crossref","is-referenced-by-count":2,"title":["Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Timo","family":"Lohrenz","sequence":"first","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Schwarz","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Li","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref33","first-page":"1","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref34","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","author":"paszke","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref10","first-page":"5884","article-title":"Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition","author":"dong","year":"2018","journal-title":"Proc of ICASSP"},{"key":"ref40","article-title":"On Using Monolingual Corpora in Neural Machine Translation","author":"g\u00fcl\u00e7ehre","year":"2015","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414920"},{"key":"ref13","article-title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","author":"pereyra","year":"2017","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards Better Decoding and Language Model Integration in Sequence to Sequence Models","author":"chorowski","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2520364"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2783545"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2409785"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268925"},{"key":"ref19","first-page":"1","article-title":"Distilling Knowledge in a Neural Network","author":"hinton","year":"2014","journal-title":"Proc of NIPS - Work-shops"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414648"},{"key":"ref3","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":"ref6","first-page":"577","article-title":"Attention-based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref5","first-page":"1","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref9","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"ArXiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","article-title":"When Does Label Smoothing Help?","author":"m\u00fcller","year":"2020","journal-title":"ArXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref23","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1223"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688298.pdf?arnumber=9688298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:28Z","timestamp":1652733688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688298","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}