{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:39:30Z","timestamp":1753601970355},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462576","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"source":"Crossref","is-referenced-by-count":32,"title":["Acoustic-to-Word Attention-Based Model Complemented with Character-Level CTC-Based Model"],"prefix":"10.1109","author":[{"given":"Sei","family":"Ueno","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirofumi","family":"Inaguma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref13","first-page":"959","article-title":"Direct acoustics-to-word models for English conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"2017"},{"key":"ref14","first-page":"3707","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2017","journal-title":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"3532","DOI":"10.21437\/Interspeech.2017-1118","article-title":"Multitask learning with low-level auxiliary tasks for encoder-decoder based speech recognition","author":"toshniwal","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref18","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"2000","journal-title":"International Conference on Language Resources and Evaluation (LREC)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.199"},{"key":"ref4","first-page":"1764","article-title":"Towards End-To-End speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of The 31 st International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","first-page":"604","article-title":"Acoustic modelling with CD-CTC-SMBR LSTM RNNs","author":"sak","year":"2015","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2015 IEEE Workshop"},{"key":"ref5","author":"sak","year":"2015","journal-title":"Fast and accurate recurrent neural network acoustic models for speech recognition"},{"key":"ref8","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: first results","author":"chorowski","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-405","article-title":"English Conversational Telephone Speech Recognition by Humans and Machines","author":"saon","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"3702","DOI":"10.21437\/Interspeech.2017-232","article-title":"An analysis of “attention","author":"prabhavalkar","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref20","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Chainer: a next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref21","first-page":"1","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"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\/08462576.pdf?arnumber=8462576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T03:16:28Z","timestamp":1598238988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462576","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}