{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:30:49Z","timestamp":1730230249155,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462210","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5814-5818","source":"Crossref","is-referenced-by-count":5,"title":["A Study of All-Convolutional Encoders for Connectionist Temporal Classification"],"prefix":"10.1109","author":[{"given":"Kalpesh","family":"Krishna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Gimpel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Residual convolutional CTC networks for automatic speech recognition","volume":"abs 1702 7793","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051584-7.50037-1"},{"key":"ref12","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-546","article-title":"Di-rect acoustics- to- word models for English conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"crossref","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":"InterSpeech"},{"key":"ref15","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1683","article-title":"Comparison of decoding strategies for CTC acoustic models","author":"zenkel","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","article-title":"Deep residual learning for image recognition","author":"he","year":"2016","journal-title":"CVPR"},{"key":"ref18","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"loffe","year":"2015","journal-title":"Proceedings of ICML"},{"key":"ref19","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"InterSpeech"},{"key":"ref6","article-title":"Deep Speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proceedings of ICML"},{"key":"ref5","article-title":"Lexicon-free conversational speech recognition with neural networks","author":"maas","year":"2015","journal-title":"HLT-NAACL"},{"key":"ref8","article-title":"Advances in all-neural speech recognition","author":"zweig","year":"2017","journal-title":"ICASSP"},{"key":"ref7","article-title":"EESEN: End-to-end speech recognition using deep RNN models and WFST -based decoding","author":"miao","year":"2015","journal-title":"ASRU"},{"key":"ref2","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"chan","year":"2016","journal-title":"ICA SSP"},{"key":"ref1","article-title":"Se-quence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1446"},{"key":"ref20","article-title":"SWITCHBOARD: Telephone speech corpus for research and development","author":"godfrey","year":"0","journal-title":"ICASSP 1992"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"journal-title":"Tensorfiow Large-scale machine learning on heterogeneous distributed systems","year":"2015","author":"abadi","key":"ref21"},{"key":"ref24","article-title":"Wav2Letter: an end-to-end convnet-based speech recognition system","volume":"abs 1609 3193","author":"collobert","year":"2016","journal-title":"CoRR"},{"key":"ref23","article-title":"SRILM-an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462210.pdf?arnumber=8462210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T02:42:12Z","timestamp":1598236932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462210","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}