In this paper, we describe a novel speaker adaptation algorithm based on Gaussian mixture weight adaptation. A small number of latent speaker vectors are estimated with non-negati...
For speech recognition, mismatches between training and testing for speaker and noise are normally handled separately. The work presented in this paper aims at jointly applying sp...
K. K. Chin, Haitian Xu, Mark J. F. Gales, Catherin...
Abstract-- Speaker space based adaptation methods for automatic speech recognition have been shown to provide significant performance improvements for tasks where only a few second...
This paper describes a new method for fast speaker adaptation in large vocabulary recognition systems. As in most HMM-based recognizers, the observation densities are modeled as a...
Jacques Duchateau, Tobias Leroy, Kris Demuynck, Hu...
This paper describes subspace constrained feature space maximum likelihood linear regression (FMLLR) for rapid adaptation. The test speaker’s FMLLR rotation matrix is decomposed...