{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T20:41:33Z","timestamp":1762029693607,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,24]]},"DOI":"10.23919\/eusipco47968.2020.9287488","type":"proceedings-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T21:54:18Z","timestamp":1608328458000},"page":"311-315","source":"Crossref","is-referenced-by-count":5,"title":["Noise-robust Attention Learning for End-to-End Speech Recognition"],"prefix":"10.23919","author":[{"given":"Yosuke","family":"Higuchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naohiro","family":"Tawara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoharu","family":"Iwata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"article-title":"RWTH ASR systems for librispeech: Hybrid vs attention-w\/o data augmentation","year":"2019","author":"l\u00fcscher","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-014-0047-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref27","article-title":"CSR-I (WSJ0) complete","volume":"ldc93s6a","author":"garofalo","year":"2007"},{"key":"ref3","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref6","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref7"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref1","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"article-title":"Invariant representations for noisy speech recognition","year":"2016","author":"serdyuk","key":"ref20"},{"key":"ref22","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639575"},{"key":"ref23","article-title":"Connection-ist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"graves","year":"2006","journal-title":"Proceedings of International Conference on Machine Learning (ICML)"},{"volume":"ldc94s13a","article-title":"CSR-II (WSJ1) complete","year":"1994","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"event":{"name":"2020 28th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2021,1,18]]},"location":"Amsterdam, Netherlands","end":{"date-parts":[[2021,1,21]]}},"container-title":["2020 28th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9287308\/9287310\/09287488.pdf?arnumber=9287488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T03:14:55Z","timestamp":1614050095000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9287488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/eusipco47968.2020.9287488","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}