{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:59:20Z","timestamp":1765231160024,"version":"3.28.0"},"reference-count":61,"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\/asru46091.2019.9003976","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"562-569","source":"Crossref","is-referenced-by-count":18,"title":["End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System"],"prefix":"10.1109","author":[{"given":"Chanwoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungsoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehul","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungmin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changwoo","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Garg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunhyang","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minkyoo","family":"Shin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shatrughan","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Larry","family":"Heck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Horovod fast and easy distributed deep learning in tensorflow","year":"2018","author":"sergeev","key":"ref39"},{"key":"ref38","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symp Operating Systems Design and Implementation (OSDI 16)"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.21437\/Interspeech.2016-1386","article-title":"Two-stage data augmentation for low-resourced speech recognition","author":"hartmann","year":"2016","journal-title":"Proc Interspeech 2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462223"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462269"},{"key":"ref37","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","author":"jaitly","year":"2013","journal-title":"Int Conf Mach Learn (ICML) Workshop on Deep Learn Audio Speech Lang Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2566"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373230"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref60","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref61","volume":"abs 1905 3072","author":"l\u00fcscher","year":"2019","journal-title":"RWTH ASR systems for LibriSpeech Hybrid vs attention - w\/o data augmentation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288950"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"729","DOI":"10.21437\/Interspeech.2010-271","article-title":"Automatic selection of thresholds for signal separation algorithms based on interaural delay","author":"kim","year":"2010","journal-title":"Proc INTERSPEECH 2010"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"751","DOI":"10.21437\/Interspeech.2015-250","article-title":"Sound source separation algorithm using phase difference and angle distribution modeling near the target","author":"kim","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"379","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3227"},{"key":"ref20","volume":"abs 1706 2677","author":"goyal","year":"2017","journal-title":"Accurate large minibatch sgd Training imagenet in 1 hour"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.07.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.21437\/Interspeech.2014-157","article-title":"Robust speech recognition using temporal masking and thresholding algorithma","author":"kim","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.21437\/Interspeech.2016-552","article-title":"Improved MVDR Beamforming Using Single-Channel Mask Prediction Networks","author":"erdogan","year":"2016","journal-title":"Proc Interspeech 2016"},{"key":"ref25","first-page":"5210","article-title":"Ro-bust MVDR beamforming using time-frequency masks for on-line\/offline ASR in noise","author":"higuchi","year":"2016","journal-title":"IEEE Int Conf Acoust Speech Signal Processing"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref58","first-page":"18","article-title":"librosa: Audio and music signal analysis in python","author":"mcfee","year":"0","journal-title":"Proceedings of the 14th Python in Science Conference"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref56","volume":"abs 1503 3535","author":"gulcehre","year":"2015","journal-title":"On using monolingual corpora in neural machine translation"},{"key":"ref55","first-page":"111-1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 ser ICML'13 JMLR org"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003936"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3216"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"399","DOI":"10.21437\/Interspeech.2017-234","article-title":"Acoustic modeling for Google Home","author":"li","year":"2017","journal-title":"Proc Interspeech 2017"},{"journal-title":"Samsung bixby","year":"0","key":"ref11"},{"journal-title":"IBM IBM Spectrum LSF Version 10 Release 1 0 Configuration Reference","year":"0","key":"ref40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref14","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref18","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 Interspeech 2017"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.21437\/Interspeech.2017-1284","article-title":"End-to-end training of acoustic models for large vocabulary continuous speech recognition with tensorflow","author":"variani","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref6","article-title":"Improving the speed of neural networks on CPUs","author":"vanhoucke","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref5","article-title":"Feature learning in deep neural networks - studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref49","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"Signal Processing for Robust Speech Recognition Motivated by Auditory Processing","year":"2010","author":"kim","key":"ref46"},{"key":"ref45","first-page":"4101","article-title":"Power-normalized cepstral coefficients (pncc) for robust speech recognition","year":"2012","journal-title":"IEEE Int Conf on Acoustics Speech and Signal Processing"},{"journal-title":"Zero mq","year":"0","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21236\/ADA333514"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1109\/TASLP.2015.2438544","article-title":"Data augmentation for deep neural network acoustic modeling","volume":"23","author":"cui","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495570"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003973"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","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\/09003976.pdf?arnumber=9003976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:51:19Z","timestamp":1658155879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003976","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}