Speech & natural language publications

We present a simple automatic segmenter of transcripts based on N-gram language modeling. We also study the relevance of several word-level features for segmentation performance. Using only word-level information, we…

Disfluencies are prevalent in spontaneous speech, and are relevant to both human speech communication and speech processing by machine. This paper reports selected results on Switchboard and two comparison corpora…

We ask whether lexical hesitations in spontaneous speech tend to precede words that are difficult to predict. We define predictability in terms of both transition probability and entropy, in the…

We study F0 variation produced by "speaking up", as part of a larger study of pitch range variation within and across speakers. We provide a function to predict target F0…

This article examines the generalization of the mental model principle to communication of a system of concepts across worldviews.

I present a unified account of interpretation preferences of stressed and unstressed pronouns in discourse. The central intuition is the Complementary Preference Hypothesis that predicts the interpretation preference of a…

We present a maximum-likelihood(ML)stochastic matching approach to decrease the acoustic mismatch between a test utterance and a given set of speech models so as to reduce the recognition performance degradation…

Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. In this…

We introduce a language model that predicts disfluencies probabilistically and uses an edited, fluent context to predict following words. It uses dynamic programming to compute the probability of a word…

In this paper we focus on transformation-based maximum-likelihood (ML) adaptation.

An acoustic confidence measure for acceptance/rejection of recognition hypotheses for continuous speech utterances is proposed. This measure is useful for rejecting utterances that are out of domain, or contain out-of-vocabulary…