{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T05:21:59Z","timestamp":1725600119065},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747344","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7787-7791","source":"Crossref","is-referenced-by-count":0,"title":["Being Greedy Does Not Hurt: Sampling Strategies for End-To-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jahn","family":"Heymann","sequence":"first","affiliation":[{"name":"Amazon.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[{"name":"Amazon.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leif","family":"Radel","sequence":"additional","affiliation":[{"name":"Amazon.com"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Promising accurate prefix boosting for sequence-to-sequence asr","year":"2018","author":"baskar","key":"ref10"},{"key":"ref11","article-title":"Sequence-to-sequence ASR optimization via reinforcement learning","author":"tjandra","year":"2017","journal-title":"CoRR"},{"key":"ref12","article-title":"Improving end-to-end speech recognition with policy learning","author":"zhou","year":"2017","journal-title":"CoRR"},{"key":"ref13","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"CoRR"},{"key":"ref14","article-title":"SEARNN: training rnns with global-local losses","author":"leblond","year":"2017","journal-title":"CoRR"},{"key":"ref15","article-title":"Learning to search better than your teacher","author":"chang","year":"2015","journal-title":"CoRR"},{"key":"ref16","article-title":"A fully differentiable beam search decoder","author":"collobert","year":"2019","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1137"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better de-coding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"ArXiv"},{"key":"ref5","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2017","journal-title":"CoRR"},{"key":"ref8","article-title":"Optimizing expected word error rate via sampling for speech recognition","author":"shannon","year":"2017","journal-title":"CoRR"},{"key":"ref7","article-title":"Minimum word error rate training for attention-based sequence-to-sequence models","author":"prabhavalkar","year":"2017","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","article-title":"Mle-guided parameter search for task loss minimization in neural sequence modeling","author":"welleck","year":"2020","journal-title":"CoRR"},{"key":"ref1","article-title":"Optimal completion distillation for sequence learning","author":"sabour","year":"2018","journal-title":"CoRR"},{"key":"ref20","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"journal-title":"SentencePiece A simple and language independent subword tokenizer and detokenizer for neural text processing","year":"2018","author":"kudo","key":"ref22"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref24","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747344.pdf?arnumber=9747344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:28Z","timestamp":1660593988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747344","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}