Author: SRI International

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 nonlinearly projecting a large set of acoustic features (e.g., several frames) to a lower-dimensional feature set.

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 the Switchboard corpus of spontaneous human-to-human telephone speech.

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.

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 experimental results.

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 entropy resulting from pruning a single N-gram can be computed exactly and efficiently for backoff models.

This study asks whether current approaches, which use mainly word information, could be improved by adding prosodic information. The study is based on more than 1000 conversations from the Switchboard corpus.