作者其他论文
文献详情
An unsupervised deep domain adaptation approach for robust speech recognition
文献类型:期刊
作者:Sun, Sining[1]  Zhang, Binbin[2]  Xie, Lei[3]  Zhang, Yanning[4]  
机构:[1]Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[2]Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[3]Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[4]Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China
通讯作者:Xie, L (reprint author), Northwestern Polytech Univ, Sch Comp Sci, Shaanxi Prov Key Lab Speech & Image Informat Proc, Xian, Peoples R China.
年:2017
期刊名称:NEUROCOMPUTING影响因子和分区
卷:257
页码范围:79-87
增刊:正刊
学科:计算机科学
收录情况:SCI(E)(WOS:000404319800009)  EI(20170803359184)  
所属部门:计算机学院
被引频次:13
人气指数:521
浏览次数:508
基金:National Natural Science Foundation of China [61571363]; National High Technology Research and Development Program of China [2015AA016402]
关键词:Domain adaptation; Robust speech recognition; Deep neural network; Deep learning
摘要:
This paper addresses the robust speech recognition problem as a domain adaptation task. Specifically, we inttoduce an unsupervised deep domain adaptation (DDA) approach to acoustic modeling in order to eliminate the training-testing mismatch that is common in real-world use of speech recognition. Under a multi-task learning framework, the approach jointly learns two discriminative classifiers using one deep neural network (DNN). As the main task, a label predictor predicts phoneme labels and is ...More
0
评论(0 条评论)
登录