Automatic speech recognition (ASR), powered by the rapid developments of machine learning technology and growing availability of computational resources, has enjoyed much success in its wide range of applications to our daily routines. In this presentation, I will give a brief overview of some attempts we had made to enhance the performance of ASR through leveraging various deep or shallow learning approaches. Furthermore, recent developments in several downstream applications of ASR, including spoken document retrieval and summarization, computer-assisted language training (CAPT), and the like, will be illustrated. Finally, I will conclude this presentation with some avenues for future work.
Berlin Chen is a Professor in the Computer Science and Information Engineering Department at National Taiwan Normal University (NTNU), Taipei, Taiwan. He received his Ph.D. degree in computer science and information engineering from National Taiwan University (NTU) in June 2001, and then joined NTNU as an Assistant Professor in August 2002. He became an Associate Professor in August 2006 and was promoted to the rank of Professor in February 2010. Prof. Chen's research interests generally lie in the areas of speech and natural language processing, multimedia information retrieval, and artificial intelligence; he is the author/coauthor of over 150 academic publications. Prof. Chen is a member of IEEE, ISCA and ACLCLP.