210 likes | 366 Views
Duration modeling for speech recognition. Presented for BBN Dr . Andrey Nikiforov Department of Applied Mathematics and Statistics State University of New York at Stony Brook. Additional topics. Computational and modeling issues improving the performance of speech recognition algorithms
E N D
Duration modeling for speech recognition Presented for BBN Dr. Andrey Nikiforov Department of Applied Mathematics and Statistics State University of New York at Stony Brook
Additional topics Computational and modeling issues improving the performance of speech recognition algorithms • Partial classification techniques • Tree-dependence covariance models in HMM • Fast search and computations for codebooks • Interpolation for acoustic space
Time calculation A B t+1 t
Time calculation (continued) A B t+1 t
State duration correction (Fant et al., 1991)
Conclusions • Representation of duration distribution via the hazard function is simple, effective and comfortable for programming • Speech recognition errors dropped by 20-25% in different tasks • Pure time spent in Viterbi search or full probability calculation increased in average by 20% compared to the conventional HMM (almost completely compensated by the reduction of computations due to more adequate modeling)
Partial classification techniques for speech recognition • Helps to create structure in speech HMMs • Useful in codebook(s) estimation • Initial estimates for HMMs and codebooks • More accurate estimates