84 search results - page 3 / 17 » Speech separation using speaker-adapted eigenvoice speech mo... |
INTERSPEECH
2010
13 years 1 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...
INTERSPEECH
2010
13 years 1 months ago
2010
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The us...
INTERSPEECH
2010
13 years 1 months ago
2010
In this work, the RWTH automatic speech recognition systems for English and German for the second Quaero evaluation campaign 2009 are presented. The systems are designed to transc...
ICASSP
2009
IEEE
14 years 29 days ago
2009
IEEE
Independent component analysis (ICA) is not only popular for blind source separation but also for unsupervised learning when the observations can be decomposed into some independe...
ICA
2012
Springer
12 years 1 months ago
2012
Springer
Abstract. The use of high level information in source separation algorithms can greatly constrain the problem and lead to improved results by limiting the solution space to semanti...