Discriminative training of Gaussian mixture models for large vocabulary speech recognition systems

  • Authors:

  • L. R. Bahl;M. Padmanabhan;D. Nahamoo;P. S. Gopalakrishnan

  • Affiliations:

  • IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA;-;-;-

  • Venue:
  • ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

Two discriminative techniques are described (and evaluated) for estimating the parameters of the Gaussians in a large vocabulary speech-recognition system. The first technique is based on using a modification of the maximum mutual information (MMI) objective function, and appears to provide no improvement over standard ML estimation. The second technique is based on a heuristic correction of the Gaussian parameters, and is seen to give a 2-5% improvement over ML estimation.