Speech & natural language publications

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…

We report results from a cross-language study of disfluencies (DFs) in Swedish and American English human-machine and human-human dialogs. We focus on differences suggestive of how speakers utilize DFs in…

This paper presents a preliminary investigation into the realization of a particular class of dialog acts which play an essential structuring role in dialog, the backchannels or acknowledgements tokens. We…

In this work, we take a first step toward capturing suprasegmental patterns for automatic speaker verification. Prosody modeling improves the verification performance of a cepstrum-based Gaussian mixture model system (as…

We describe the methodologies for collecting and annotating a Latin-American Spanish speech database. We use the annotated database to investigate rater reliability, the effect of each phone on overall perceived…

The rapid growth in the number of companies devoted to speech recognition applications attests to this growth in performance. This brief report explores the further potential for speech technology.

This article provides a succinct review of the history and current status of the field of speech processing research and describes future contributions speech processing will make to society.

We study a nonlinear discriminant analysis (NLDA) technique that extracts a speaker-discriminant feature set. Our approach is to train a multilayer perceptron (MLP) to maximize the separation between speakers by…

We describe an integrated approach for statistical modeling of discourse structure for natural conversational speech. Our model is based on 42 `dialog acts', which were hand-labeled in 1155 conversations from…

This paper describes SRI's 1997 broadcast news transcription system used for the 1997 DARPA H4 evaluations. Our system had several novel components. We briefly describe these features and give comparative…

In this paper we describe the development of the Voice Interactive Language Training System (VILTS) and our experience in exploring the potential of speech technology in service to language learning.

A criterion for pruning parameters from N-gram backoff language models is developed, based on the relative entropy between the original and the pruned model. It is shown that the relative…