Author: SRI International

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 about production processes, and can guide methods for disfluency processing in speech recognition applications.

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 data, and concentrates on two approaches: extracting features that are robust against channel variations, and transforming the speaker models to compensate for channel effects.

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 as duration and pitch.

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 allow sentence and topic segmentation that is at least as good as word-based methods alone, and that combining both types of cues gives significant wins.

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 the word-based performance metric and the standard MAP scoring paradigm that is sentence-based, and that can lead to sub-optimal recognition results.