Advances in Punctuation and Disfluency Prediction

With the advancement of automatic speech recognition (ASR) technology, more and more natural language processing (NLP) applications have been used in our daily life, such as spoken language translation, automatic question answering, speech information retrieval, etc. When dealing with recognized spontaneous speech, several natural problems arise. Firstly, recognized speech does not have punctuation or sentence boundary information. Secondly, spontaneous speech contains disfluency which carries no useful content information. The lack of punctuation and sentence boundary information and the presence of disfluency affect the performance of downstream NLP tasks. Thus, the goal of this work is to develop or improve algorithms to automatically detect sentence boundaries, add punctuation, and identify disfluent words in recognized speech so as to improve the performance of downstream NLP tasks.