Sciweavers

ICASSP
2011
IEEE
13 years 4 months ago
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we pro...
George E. Dahl, Dong Yu, Li Deng, Alex Acero
TASLP
2010
122views more  TASLP 2010»
13 years 7 months ago
Error Approximation and Minimum Phone Error Acoustic Model Estimation
Minimum phone error (MPE) acoustic parameter estimation involves calculation of edit distances (errors) between correct and incorrect hypotheses. In the context of large vocabulary...
Matt Gibson 0002, Thomas Hain
CSL
2007
Springer
14 years 8 days ago
Discriminative semi-parametric trajectory model for speech recognition
Hidden Markov Models (HMMs) are the most commonly used acoustic model for speech recognition. In HMMs, the probability of successive observations is assumed independent given the ...
K. C. Sim, M. J. F. Gales