249 search results - page 11 / 50 » Subspace Gaussian Mixture Models for speech recognition |
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
ICASSP
2010
IEEE
14 years 9 months ago
2010
IEEE
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
ICPR
2010
IEEE
14 years 7 months ago
2010
IEEE
We propose the use of the line spectral frequency (LSF) features for emotion recognition from speech, which have not been been previously employed for emotion recognition to the b...
TASLP
2010
14 years 4 months ago
2010
The knowledge of the target speech presence probability in a mixture of signals captured by a speech communication system is of paramount importance in several applications includi...
NAACL
1994
14 years 11 months ago
1994
A new mapping algorithm for speech recognition relates the features of simultaneous recordings of clean and noisy speech. The model is a piecewise nonfinear transformation appfied...