29 search results - page 1 / 6 » Bayesian discriminative adaptation for speech recognition |
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
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...
CSL
2010
Springer
13 years 4 months ago
2010
Springer
NAACL
2007
13 years 6 months ago
2007
This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Ar...
ACL
2010
13 years 2 months ago
2010
We investigate a recently proposed Bayesian adaptation method for building style-adapted maximum entropy language models for speech recognition, given a large corpus of written la...