Showing papers by "Michael S. Phillips published in 1992"
Proceedings Article•
01 Jan 1992
TL;DR: This paper describes an approach in which the determination of the acoustic measurements is formulated as a constrained search problem, and the constraints are provided through a set of generic measurement primitives based on knowledge of acoustic phonetics.
25 citations
23 Feb 1992
TL;DR: This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer, which include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made toThe lexicon.
Abstract: This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer. These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. Together with the use of a larger training set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. The weighted error for the entire spoken language system on the same test set is 49.3%. Similar results were also obtained on the February '92 benchmark evaluation.
19 citations
Proceedings Article•
01 Jan 1992
3 citations
23 Feb 1992
TL;DR: In this article, the authors document their involvement in the development of WSJ-CSR corpus from recording and transcription to analyses and distribution, and present the results of an experiment investigating the preprocessing of the prompt text.
Abstract: Recently, the DARPA community started a new data collection initiative in the Wall Street Journal (WSJ) domain to support research and development of very large vocabulary continuous speech recognition (CSR) systems. Since August 1991, our group has actively participated in the development of the WSJ-CSR corpus. The purpose of this paper is to document our involvement in this process, from recording and transcription to analyses and distribution. We will also present the results of an experiment investigating the preprocessing of the prompt text.
3 citations