72 search results - page 1 / 15 » Language model cross adaptation for LVCSR system combination |
INTERSPEECH
2010
12 years 11 months ago
2010
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptatio...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Polish is a synthetic language with a high morpheme-perword ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high Language Mo...
ICASSP
2011
IEEE
12 years 8 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...
INTERSPEECH
2010
12 years 11 months ago
2010
This paper presents our latest efforts toward LVCSR systems for five Eastern European languages such as Bulgarian, Croatian, Czech, Polish, and Russian using our Rapid Language Ad...
CLEF
2004
Springer
13 years 8 months ago
2004
Springer
This paper presents the results of the State University of New York at Buffalo (UB) in the Mono-lingual and Multi-lingual tasks at CLEF 2004. For these tasks we used an approach ba...