Acoustic adaptation using nonlinear transformations of HMM parameters

  • Authors:

  • V. Abrash;A. Sankar;H. Franco;M. Cohen

  • Affiliations:

  • Speech Res. & Technol. Lab., SRI Int., Menlo Park, CA, 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

Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. We extend this approach to use nonlinear transformations. These are implemented by multilayer perceptrons (MLPs) which transform the Gaussian means. We derive a generalized expectation-maximization (GEM) training algorithm to estimate the MLP weights. Some preliminary experimental results on nonnative speaker adaptation are presented.