Applying SPHINX-II to the DARPA Wall Street Journal CSR task

Authors:
F. Alleva;H. Hon;X. Huang;M. Hwang;R. Rosenfeld;R. Weide
Affiliations:
Carnegie Mellon University, Pittsburgh, Pennsylvania;Carnegie Mellon University, Pittsburgh, Pennsylvania;Carnegie Mellon University, Pittsburgh, Pennsylvania;Carnegie Mellon University, Pittsburgh, Pennsylvania;Carnegie Mellon University, Pittsburgh, Pennsylvania;Carnegie Mellon University, Pittsburgh, Pennsylvania
Venue:
HLT '91 Proceedings of the workshop on Speech and Natural Language
Year:
1992

Citing 6
Cited 3

New results with the Lincoln tied-mixture HMM CSR system

HLT '91 Proceedings of the workshop on Speech and Natural Language
A study on speaker-adaptive speech recognition

HLT '91 Proceedings of the workshop on Speech and Natural Language
Improved hidden Markov modeling for speaker-independent continuous speech recognition

HLT '90 Proceedings of the workshop on Speech and Natural Language
The SPHINX-II Speech Recognition System: An Overview

The SPHINX-II Speech Recognition System: An Overview
Text on tap: the ACL/DCI

HLT '89 Proceedings of the workshop on Speech and Natural Language
The design for the wall street journal-based CSR corpus

HLT '91 Proceedings of the workshop on Speech and Natural Language

DARPA February 1992 pilot corpus CSR "dry run" benchmark test results

HLT '91 Proceedings of the workshop on Speech and Natural Language
An overview of the SPHINX-II speech recognition system

HLT '93 Proceedings of the workshop on Human Language Technology
A one pass decoder design for large vocabulary recognition

HLT '94 Proceedings of the workshop on Human Language Technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper reports recent efforts to apply the speaker-independent SPHINX-II system to the DARPA Wall Street Journal continuous speech recognition task. In SPHINX-II, we incorporated additional dynamic and speaker-normalized features, replaced discrete models with sex-dependent semi-continuous hidden Markov models, augmented within-word triphones with between-word triphones, and extended generalized triphone models to shared-distribution models. The configuration of SPHINX-II being used for this task includes sex-dependent, semi-continuous, shared-distribution hidden Markov models and left context dependent between-word triphones. In applying our technology to this task we addressed issues that were not previously of concern owing to the (relatively) small size of the Resource Management task.