Discriminative mixture weight estimation for large Gaussian mixture models

Authors:
F. Beaufays;M. Weintraub;Yochai Konig
Affiliations:
Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA;-;-
Venue:
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Year:
1999

Citing 0
Cited 2

Acoustic Feature Analysis and Discriminative Modeling of Filled Pauses for Spontaneous Speech Recognition

Journal of VLSI Signal Processing Systems
A recursive method for discriminative mixture learning

Proceedings of the 24th international conference on Machine learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a new approach to acoustic modeling for large vocabulary continuous speech recognition (LVCSR) systems. Each phone is modeled with a large Gaussian mixture model (GMM) whose context-dependent mixture weights are estimated with a sentence-level discriminative training criterion. The estimation problem is cast in a neural network framework, which enables the incorporation of the appropriate constraints on the mixture weight vectors, and allows a straight-forward training procedure, based on steepest descent. Experiments conducted on the Callhome-English and Switchboard databases show a significant improvement of the acoustic model performance, and a somewhat lesser improvement with the combined acoustic and language models.