Unsupervised modeling of latent topics and lexical units in speech audio

Abstract

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.