{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:54:55Z","timestamp":1730199295142,"version":"3.28.0"},"reference-count":33,"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\/asru46091.2019.9003936","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"70-77","source":"Crossref","is-referenced-by-count":13,"title":["Improved Multi-Stage Training of Online Attention-Based Encoder-Decoder Models"],"prefix":"10.1109","author":[{"given":"Abhinav","family":"Garg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Kumar","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":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Jasper An end-to-end convolutional neural acoustic model","year":"2019","author":"jason","key":"ref33"},{"key":"ref32","article-title":"The CAPIO 2017 conversational speech recognition system","volume":"abs 1801 59","author":"han","year":"2018","journal-title":"CoRR"},{"key":"ref31","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1452"},{"key":"ref11","article-title":"Un-supervised pretraining for sequence to sequence learning","author":"prajit","year":"2016","journal-title":"EMNLP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref17","article-title":"Flatstart-ctc: a new acoustic model training procedure for speech recognition","author":"senior","year":"2016","journal-title":"ICASSP 2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint etc-attention based end-to-end speech recognition with a deep cnn encoder and rnn-lm","author":"hori","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","volume":"12","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref4","first-page":"939","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"rohit","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"journal-title":"SpecAugment A simple data augmentation method for automatic speech recognition","year":"2019","author":"park","key":"ref3"},{"key":"ref6","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume":"70","author":"raffel","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref29","article-title":"On using monolingual corpora in neural machine translation","volume":"abs 1503 3535","author":"gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref5","first-page":"6381","article-title":"Streaming end-to-end speech recognition for mobile devices","author":"yanzhang","year":"2019","journal-title":"ICASSP 2019–2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"6th International Conference on Learning Representations ICLR 2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4022"},{"key":"ref9","article-title":"Improved training for online end-to-end speech recognition systems","author":"suyoun","year":"2017","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref24","first-page":"1929","article-title":"Dropout: Asimple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"brian","year":"2015","journal-title":"Proceedings of the 14th Python in Science Conference"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"ref25","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"}],"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\/09003936.pdf?arnumber=9003936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:51:20Z","timestamp":1658155880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003936","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}