16 search results - page 2 / 4 » On maximum mutual information speaker-adapted training |
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
In the symbol recognition stage of online handwritten math expression recognition, the one-pass dynamic programming algorithm can produce high-quality symbol graphs in addition of...
ICASSP
2010
IEEE
13 years 5 months ago
2010
IEEE
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
ICASSP
2009
IEEE
14 years 3 days ago
2009
IEEE
This paper considers a method for speech emotion recognition by a max-margin framework incorporating a loss function based on a well-known model called the Watson and Tellegen’s...