255 search results - page 2 / 51 » On the use of speaker superfactors for speaker recognition |
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Research in the speaker recognition community has continued to address methods of mitigating variational nuisances. Telephone and auxiliary-microphone recorded speech emphasize th...
ICASSP
2011
IEEE
12 years 10 months ago
2011
IEEE
A common problem in speech recognition for foreign accented speech is that there is not enough training data for an accent-specific or a speaker-specific recognizer. Speaker ada...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
We present a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where th...
INTERSPEECH
2010
13 years 29 days ago
2010
Most of current speaker recognition systems are based on features extracted from the magnitude spectrum of speech. However the excitation signal produced by the glottis is expecte...
TSD
2004
Springer
13 years 11 months ago
2004
Springer
In this paper a speaker adaptation methodology is proposed, which first automatically determines a number of speaker clusters in the training material, then estimates the paramete...