The SPHINX speech recognition system - Robotics Institute Carnegie Mellon University

The SPHINX speech recognition system

K.-F. Lee, H.-W. Hon, M.-Y. Hwang, S. Mahajan, and Raj Reddy
Conference Paper, Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP '89), Vol. 1, pp. 445 - 448, May, 1989

Abstract

A description is given of SPHINX an accurate large-vocabulary speaker-independent continuous speech recognition system. The authors have made several recent enhancements, including generalized triphone models, word duration modeling, function-phrase modeling, between-word coarticulation modeling, and corrective training. On the 997-word resource management task, SPHINX attained a word accuracy of 96% with a grammar (perplexity 60), and 82% without grammar (perplexity 997).

BibTeX

@conference{Lee-1989-15479,
author = {K.-F. Lee and H.-W. Hon and M.-Y. Hwang and S. Mahajan and Raj Reddy},
title = {The SPHINX speech recognition system},
booktitle = {Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP '89)},
year = {1989},
month = {May},
volume = {1},
pages = {445 - 448},
}