L. Deng, Jinyu Li, J. Huang, K. Yao, Dong Yu, F. Seide, M. Seltzer, G. Zweig, Xiaodong He, J. Williams, Y. Gong, A. Acero
{"title":"Recent advances in deep learning for speech research at Microsoft","authors":"L. Deng, Jinyu Li, J. Huang, K. Yao, Dong Yu, F. Seide, M. Seltzer, G. Zweig, Xiaodong He, J. Williams, Y. Gong, A. Acero","doi":"10.1109/ICASSP.2013.6639345","DOIUrl":null,"url":null,"abstract":"Deep learning is becoming a mainstream technology for speech recognition at industrial scale. In this paper, we provide an overview of the work by Microsoft speech researchers since 2009 in this area, focusing on more recent advances which shed light to the basic capabilities and limitations of the current deep learning technology. We organize this overview along the feature-domain and model-domain dimensions according to the conventional approach to analyzing speech systems. Selected experimental results, including speech recognition and related applications such as spoken dialogue and language modeling, are presented to demonstrate and analyze the strengths and weaknesses of the techniques described in the paper. Potential improvement of these techniques and future research directions are discussed.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"770","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.2013.6639345","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 770
Abstract
Deep learning is becoming a mainstream technology for speech recognition at industrial scale. In this paper, we provide an overview of the work by Microsoft speech researchers since 2009 in this area, focusing on more recent advances which shed light to the basic capabilities and limitations of the current deep learning technology. We organize this overview along the feature-domain and model-domain dimensions according to the conventional approach to analyzing speech systems. Selected experimental results, including speech recognition and related applications such as spoken dialogue and language modeling, are presented to demonstrate and analyze the strengths and weaknesses of the techniques described in the paper. Potential improvement of these techniques and future research directions are discussed.