当前位置 :

新闻中心

关于俞栋博士学术报告的通知

  讲座题目:Single-Channel Mixed Speech Recognition Using Deep Neural Networks

  主讲嘉宾:Dr. Dong Yu (Microsoft Research)

  时    间:2014年5月28日15:30-16:30

  地    点:科大西区科技实验西楼一楼117会议室

  主办单位:语音及语言信息处理国家工程实验室

  报告摘要:

  While significant progress has been made in improving the noise robustness of speech recognition systems, recognizing speech in the presence of a competing talker remains one of the most challenging unsolved problems in the field. In this talk, I will present our first attempt in attacking this problem using deep neural networks (DNNs). Our approach adopted a multi-style training strategy using artificially mixed speech data. I will discuss the strengths and weaknesses of several different setups that we have investigated including a WFST-based two-talker decoder to work with the trained DNNs. Experiments on the 2006 speech separation and recognition challenge task demonstrate that the proposed DNN-based system has remarkable noise robustness to the interference of a competing speaker. The best setup of our proposed systems achieves an overall WER of 19.7% which improves upon the results obtained by the state-of-the-art IBM superhuman system by 1.9% absolute, with fewer assumptions and lower computational complexity.

  嘉宾简介:

  Dr. Dong Yu is a principal researcher at the Microsoft speech and dialog research group and a guest professor of university of science and technology of China. His research interests include speech processing, robust speech recognition, discriminative training, and machine learning. He has published over 130 papers in these areas and is the co-inventor of more than 50 granted/pending patents. His most recent work on the context-dependent deep neural network hidden Markov model (CD-DNN-HMM), which was recognized by the IEEE SPS 2013 best paper award, has been seriously challenging the dominant position of the conventional GMM based system for large vocabulary speech recognition.