Speech & natural language publications

We describe SRI's large vocabulary conversational speech recognition system as used in the March 2000 NIST Hub-5E evaluation.

As with acoustic modelling, sparse training data is one of the main problems in language modelling tasks. We ideally want to have enough properly matched data to train models for…

Using decision tree and hidden Markov modeling techniques, we combine prosodic cues with word-based approaches, and evaluate performance on two speech corpora, Broadcast News and Switchboard. Results show that the…

Analyses of American English show that disfluency affects a variety of phonetic aspects of speech, including segment durations, intonation, voice quality, vowel quality, and coarticulation patterns. These effects provide clues…

This study delves into the acoustic and prosodic information of repetitions, one of the most common disfluencies. A hierarchical clustering of prosodic features reveals three subsets of repetitions, each reflecting…

We describe a new algorithm for finding the hypothesis in a recognition lattice that is expected to minimize the word error rate (WER). Our approach thus overcomes the mismatch between…

We investigate a new approach for using speech prosody as a knowledge source for speech recognition. The idea is to penalize word hypotheses that are inconsistent with prosodic features such…

In this work we demonstrate the use of em prosodic cues, alone and in combination with words, for segmentation and name finding. In experiments, we find that prosodic cues alone…

This paper addresses the issue of closed-set text-independent speaker identifcation from samples of speech recorded over the telephone. It focuses on the effects of acoustic mismatches between training and testing…

We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topic units. The approach combines hidden Markov models, statistical language models,…

We describe two new techniques for reducing word lattice sizes without eliminating hypotheses.

We propose a quantitative model that predicts the overall distribution of retrace lengths in a large corpus of spontaneous speech, based only on word position. Results have implications for modeling…