Recognizing Structure in Report Transcripts

Abstract

Typically, the output of Automatic Speech Recognition (ASR) is a mere sequence of words. This view may be sufficient for some tasks, whereas others require a more structured approach. This thesis presents a framework that allows for identification of deep, underlying structure in report dictations. Identification of structural elements, such as headings, sections and enumerations is an important step towards automatic post-processing of dictated speech. The contributions of this thesis include a generic approach that can be integrated seamlessly with existing ASR solutions and provides structured output, as well as a freely available Conditional Random Field (CRF) toolkit that forms the basis of the aforementioned approach and may also be applicable to numerous other problems.