249 search results - page 26 / 50 » Subspace Gaussian Mixture Models for speech recognition |
ICDAR
2003
IEEE
15 years 3 months ago
2003
IEEE
In off-line handwriting recognition, classifiers based on hidden Markov models (HMMs) have become very popular. However, while there exist well-established training algorithms, s...
100
click to vote
TASLP
2011
14 years 4 months ago
2011
—We present a simple and efficient feature modeling approach for tracking the pitch of two simultaneously active speakers. We model the spectrogram features of single speakers u...
TASLP
2010
14 years 4 months ago
2010
In the presence of environmental noise, speakers tend to adjust their speech production in an effort to preserve intelligible communication. The noise-induced speech adjustments, c...
INTERSPEECH
2010
14 years 4 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...
ACSC
2006
IEEE
15 years 3 months ago
2006
IEEE
This paper describes a novel noise-robust automatic speech recognition (ASR) front-end that employs a combination of Mel-filterbank output compensation and cumulative distribution...