{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T09:21:48Z","timestamp":1778145708492,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462456","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5639-5643","source":"Crossref","is-referenced-by-count":32,"title":["Robust Speech Recognition Using Generative Adversarial Networks"],"prefix":"10.1109","author":[{"given":"Anuroop","family":"Sriram","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heewoo","family":"Jun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Satheesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proceedings of The 33rd International Conference on Machine Learning, New York, New York, USA, 20\u201322 Jun 2016, vol. 48 of Proceedings of Machine Learning Research","author":"Amodei"},{"key":"ref2","volume-title":"Achieving human parity in conversational speech recognition","author":"Xiong","year":"2016"},{"key":"ref3","article-title":"Deep learning for environmentally robust speech recognition: An overview of recent developments","volume":"abs\/1705.10874","author":"Zixing","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.02.006"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref6","volume-title":"End-to-end attention-based large vocabulary speech recognition","volume":"abs\/1508.04395","author":"Bahdanau","year":"2015"},{"key":"ref7","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-015-0246-6"},{"key":"ref9","article-title":"A network of deep neural net-works for distant speech recognition","volume":"abs\/1703.08002","author":"Ravanelli","year":"2017","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-640"},{"issue":"1","key":"ref11","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref13","article-title":"Invariant representations for noisy speech recognition","volume":"abs\/1612.01928","author":"Serdyuk","year":"2016","journal-title":"CoRR"},{"key":"ref14","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Arjovsky"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref16","doi-asserted-by":"crossref","volume-title":"Exploring neural transducers for end-to-end speech recognition","author":"Battenberg","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref17","volume-title":"Rectifier nonlinearities improve neural network acoustic models","author":"Maas","year":"2013"},{"key":"ref18","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"abs\/1502.03167","author":"Ioffe","year":"2015","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-234"}],"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\/08462456.pdf?arnumber=8462456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T19:31:32Z","timestamp":1706038292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462456","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}