Unsupervised modeling of latent topics and lexical units in speech audio

• Main Author: Harwath, David F. (David Frank)
• Other Authors: James R. Glass and Timothy J. Hazen.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2013
• Subjects: Electrical Engineering and Computer Science.
• Online Access: http://hdl.handle.net/1721.1/82395

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013. === Cataloged from PDF version of thesis. === Includes bibliographical references (p. 67-70). === Zero-resource speech processing involves the automatic analysis of a collection of speech data in a completely unsupervised fashion without the benefit of any transcriptions or annotations of the data. In this thesis, we describe a zero-resource framework that automatically discovers important words, phrases and topical themes present in an audio corpus. This system employs a segmental dynamic time warping (S-DTW) algorithm for acoustic pattern discovery in conjunction with a probabilistic model which treats the topic and pseudo-word identity of each discovered pattern as hidden variables. By applying an Expectation-Maximization (EM) algorithm, our method estimates the latent probability distributions over the pseudo-words and topics associated with the discovered patterns. Using this information, we produce informative acoustic summaries of the dominant topical themes of the audio document collection. === by David F. Harwath. === S.M.