Sentence unit detection using lexical information for automatic speech recognition transcripts

Abstract

This thesis studies Sentence Unit Detection (SUD) that uses lexical information for Automatic Speech Recognition (ASR) transcripts. An SUD system detects the presence or absence of a sentence unit boundary at every word boundaries of an unpunctuated text document. A transcript produced by an ASR system from a given speech audio input is an unpunctuated text document. Hence, SUD for ASR transcripts will increase the readability and enable the usability of ASR transcripts in downstream text processing applications, such as machine translation and option mining, which require sentence unit boundary information in their input. As usually being a post-processing application for ASR transcripts, an SUD system may benefit from two major information sources, i.e., the prosodic information obtained from the audio input and the lexical information obtained from the ASR transcripts, for its model learning. In this thesis, we chose to use only lexical information because it has shown to be essential for SUD research as compared to the other. Moreover, using lexical information takes an advantage of the massive available lexical data sources from the Internet. Additionally, SUD models that use only lexical information are usually much less complex as compared to the models that employ multiple information sources. To improve an SUD system performance, one possible direction is to improve the quality of input features. Previous studies usually paid more attention on finding new input features to enrich and enlarge the existing feature space rather than refining it for a better quality. This tendency might lead to feature redundancy and unnecessarily increase the model complexity. This thesis addresses the lack in research by studying approaches that fine tune existing lexical features to SUD systems. Specifically, there are two proposed approaches: The first approach focuses on optimizing the existing features to reduces the input feature space size. The second study focuses on evaluating i Acknowledgement I want to express my sincerest thanks to my supervisor, Dr.Chng Eng Siong, for his invaluable support and guidance. I also thank all my colleagues in Temasek Laboratories @NTU and the SCSE Speech Recognition team, who are not only co-workers but also friends. Especially, I would like to thanks Dr. Chong Tze Yuang, Ms. Vu Thi Ly, Mr. Xu Chenglin, Ms. Aditi Ghosh and Mr. Can Duy Cat for the help and support they have given to me. Last but not least, thanks to my family for their unconditional love, support, and encouragement. Without them, my research life would be much harder. I also want to give a special thanks to my husband and my little girl for always being beside me, whatever and whenever, the situation.