{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:59:31Z","timestamp":1774162771068,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706651","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"121-125","source":"Crossref","is-referenced-by-count":9,"title":["Data Augmentation using Conditional Generative Adversarial Networks for Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Peiyao","family":"Sheng","sequence":"first","affiliation":[]},{"given":"Zhuolin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hu","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref32","article-title":"Aurora working group: Dsr front end lvcsr evaluation au\/384\/02","author":"pearce","year":"2002","journal-title":"Inst for Signal and Information Process"},{"key":"ref31","article-title":"Generative adversarial network based acoustic scene training set augmentation and selection using svm hyper-plane","author":"seongkyu mun","year":"2017","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"key":"ref30","article-title":"Conditional generative adversarial nets classifier for spoken language identification","author":"peng shen","year":"2017","journal-title":"INTERSPEECH 2017 - 18th Annual Conference of the International Speech Communication Association"},{"key":"ref36","author":"paszke","year":"2017","journal-title":"PyTorch"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref34","author":"yu","year":"2014","journal-title":"An Introduction to Computational Networks and the Computational Network Toolkit"},{"key":"ref10","first-page":"379","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for farfield speech recognition in google home","author":"kim","year":"2017","journal-title":"INTERSPEECH 2017 - 18th Annual Conference of the International Speech Communication Association"},{"key":"ref11","article-title":"Unsupervised domain adaptation for robust speech recognition via variational autoencoder-based data augmentation","volume":"7","author":"hsu","year":"2017","journal-title":"ASRU"},{"key":"ref12","volume":"10","author":"ghaffarzadegan","year":"2017","journal-title":"Deep neural network training for whispered speech recognition using small databases and generative model sampling"},{"key":"ref13","article-title":"Generative adversarial networks based data augmentation for noise robust speech recognition","author":"hu","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Improved techniques for training gans","volume":"abs 1606 3498","author":"salimans","year":"2016","journal-title":"CoRR"},{"key":"ref16","article-title":"Learning from simulated and unsupervised images through adversarial training","volume":"abs 1612 7828","author":"shrivastava","year":"2016","journal-title":"CoRR"},{"key":"ref17","article-title":"Conditional generative adversarial nets","volume":"abs 1411 1784","author":"mirza","year":"2014","journal-title":"CoRR"},{"key":"ref18","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans","author":"odena","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning ICML 2017"},{"key":"ref19","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2016","journal-title":"ArXiv"},{"key":"ref28","article-title":"Exploring speech enhancement with generative adversarial networks for robust speech recognition","volume":"abs 1711 5747","author":"donahue","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2198059"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref27","first-page":"40","article-title":"Adversarial training for data-driven speech enhancement without parallel corpus","volume":"12","author":"higuchi","year":"2017","journal-title":"ASRU"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref29","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref5","author":"pearce","year":"2002","journal-title":"Aurora Working Group DSR Front End LVCSR Evaluation AU\/384\/02"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825432"},{"key":"ref7","article-title":"Noise robust speech recognition on aurora4 by humans and machines","author":"qian","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref2","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc Inter-speech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","first-page":"5220","article-title":"A study on data augmentation of reverberant speech for robust speech recognition","author":"ko","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref20","article-title":"Wasserstein GAN","volume":"abs 1701 7875","author":"arjovsky","year":"2017","journal-title":"CoRR"},{"key":"ref22","first-page":"4910","article-title":"Generative adversarial network-based postfilter for statistical parametric speech synthesis","author":"kaneko","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref21","article-title":"Towards principled methods for training generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"arXiv preprint arXiv 1701 04862"},{"key":"ref24","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","volume":"abs 1704 849","author":"hsu","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"Statistical parametric speech synthesis incorporating generative adversarial networks","author":"saito","year":"2017","journal-title":"IEEE Trans Audio Speech & Language Processing"},{"key":"ref26","article-title":"SEGAN: speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"CoRR"},{"key":"ref25","first-page":"4910","article-title":"Generative adversarial network-based postfilter for statistical parametric speech synthesis","author":"kaneko","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Taipei City, Taiwan","start":{"date-parts":[[2018,11,26]]},"end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706651.pdf?arnumber=8706651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:10:35Z","timestamp":1598224235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706651","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}