Comparing and Combining Generative and Posterior Probability Models: Some Advances in Sentence Boundary Detection in Speech

Abstract

We compare and contrast two different models for detecting sentence-like units in continuous speech. The first approach uses hidden Markov sequence models based on N-grams and maximum likelihood estimation, and employs model interpolation to combine different representations of the data. The second approach models the posterior probabilities of the target classes; it is discriminative and integrates multiple knowledge sources in the maximum entropy (maxent) framework. Both models combine lexical, syntactic, and prosodic information. We develop a technique for integrating pre-trained probability models into the maxent framework, and show that this approach can improve on an HMM-based state-of-the-art system for the sentence-boundary detection task. An even more substantial improvement is obtained by combining the posterior probabilities of the two systems.