{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:43:08Z","timestamp":1729672988742,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462245","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5839-5843","source":"Crossref","is-referenced-by-count":11,"title":["SEQUENCE TRAINING OF ENCODER-DECODER MODEL USING POLICY GRADIENT FOR END- TO-END SPEECH RECOGNITION"],"prefix":"10.1109","author":[{"given":"Shigeki","family":"Karita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref11","first-page":"1","article-title":"An actor-critic algorithm for sequence prediction","author":"bahdanau","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref12","first-page":"4945","article-title":"End-to-end attention-based large vocabulary speech recognition","author":"bahdanau","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","first-page":"3528","article-title":"Gra-dient estimation using stochastic computation graphs","author":"schulman","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref14","first-page":"3537","article-title":"Optimizing expected word error rate via sampling for speech recognition","author":"shannon","year":"2017","journal-title":"Proceedings of International Conference on Spoken Language Processing Interspeech"},{"key":"ref15","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","volume":"37","author":"xu","year":"0","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref17","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref18","article-title":"TED-LIUM: An automatic speech recognition dedicated corpus","author":"rousseau","year":"2012","journal-title":"Proceedings of the Eight International Conference on Language Resources and Evaluation"},{"key":"ref19","first-page":"1631","article-title":"Backstitch: Counteracting finite-sample bias via negative steps","author":"wang","year":"2017","journal-title":"Proceedings of International Conference on Spoken Language Processing Interspeech"},{"key":"ref4","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref3","first-page":"647","article-title":"Connectionist speech recognition","volume":"247","author":"bourlard","year":"1994","journal-title":"International Journal on Pattern Recognition and Artificial Intelligence"},{"key":"ref6","first-page":"4280","article-title":"Learning acoustic frame labeling for speech recognition with recurrent neural networks","author":"sak","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","first-page":"6364","article-title":"Real-time one-pass decoding with recurrent neural network language model for speech recognition","author":"hori","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","first-page":"2406","article-title":"Hypothesis spaces for minimum bayes risk training in large vocabulary speech recognition","volume":"5","author":"gibson","year":"2006","journal-title":"Proceedings of International Conference on Spoken Language Processing Interspeech"},{"key":"ref2","first-page":"4845","article-title":"Very deep convolutional networks for end-to-end speech recognition","author":"zhang","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"1","article-title":"Task loss estimation for sequence prediction","author":"bahdanau","year":"2016","journal-title":"In International Conference on Learning Representations Workshop"},{"key":"ref20","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref21","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"}],"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\/08462245.pdf?arnumber=8462245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T09:06:30Z","timestamp":1693904790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462245","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}