9 search results - page 1 / 2 » Fast speaker adaptation using non-negative matrix factorizat... |
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
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...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
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...
JMLR
2010
13 years 3 months ago
2010
Sparse coding—that is, modelling data vectors as sparse linear combinations of basis elements—is widely used in machine learning, neuroscience, signal processing, and statisti...
SCIA
2009
Springer
13 years 11 months ago
2009
Springer
In this paper, we present an efficient system for action recognition from very short sequences. For action recognition typically appearance and/or motion information of an action ...
NIPS
2008
13 years 6 months ago
2008
How does one extract unknown but stereotypical events that are linearly superimposed within a signal with variable latencies and variable amplitudes? One could think of using temp...