140 search results - page 2 / 28 » On using Articulatory Features for Discriminative Speaker Ad... |
ICCV
2005
IEEE
13 years 10 months ago
2005
IEEE
We present an approach to detecting and recognizing spoken isolated phrases based solely on visual input. We adopt an architecture that first employs discriminative detection of ...
INTERSPEECH
2010
12 years 11 months ago
2010
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs ar...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
This paper describes a speaker discrimination experiment in which native English listeners were presented with natural and synthetic speech stimuli in English and were asked to ju...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Feature-space transforms such as feature-space maximum likelihood linear regression (FMLLR) are very effective speaker adaptation technique, especially on mismatched test data. In...