Gouv�a, Evandro - Department of Electrical and Computer Engineering, Carnegie Mellon University

E-print Network

FAQ • HELP • SITE MAP • CONTACT US

Powered by Explorit

Advanced Search

Gouv�a, Evandro - Department of Electrical and Computer Engineering, Carnegie Mellon University

This paper describes recent efforts by the CMU speech group to address the important problems of robustness to changes in envi-
Speaker-dependent automatic speech recognition systems are known to outperform speaker-independent systems when
Speech recognition systems perform poorly on speech degraded by even simple effects such as linear filtering and additive noise.
CEPSTRAL COMPENSATION BY POLYNOMIAL APPROXIMATION FOR ENVIRONMENT-INDEPENDENT SPEECH RECOGNITION
In this paper we introduce a new family of environmental com-pensation algorithms called Multivariate Gaussian Based Cepstral
ACOUSTICFEATUREBASED FREQUENCY WARPING FOR
ACOUSTIC-FEATURE-BASED FREQUENCY WARPING FOR