127 search results - page 2 / 26 » Advances in Large Vocabulary Continuous Speech Recognition |
ICASSP
2009
IEEE
14 years 1 months ago
2009
IEEE
In this paper we propose discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition tasks. After presenting our hierarchical modeli...
ICASSP
2009
IEEE
14 years 1 months ago
2009
IEEE
We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation...
TASLP
2008
13 years 6 months ago
2008
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
ICASSP
2011
IEEE
12 years 10 months ago
2011
IEEE
Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
ICMCS
2009
IEEE
13 years 4 months ago
2009
IEEE
Parallel scalability allows an application to efficiently utilize an increasing number of processing elements. In this paper we explore a design space for parallel scalability for...