Acoustic model creation method for speech recognition, apparatus thereof, program thereof and recording medium thereof, speech recognition apparatus using acoustic model

摘要

PROBLEM TO BE SOLVED: To obtain an acoustic model of high performance with a small learning data volume and to obtain the acoustic model by relatively simple calculation.;SOLUTION: A variational Bayesian evaluation function is given by formula 1 wherein O is time series feature quantity vectors of leaning data, =(_c:c=1 to C), _c is model parameters of phoneme categories c, Z is an HMM status variable sequence or a gaussian mixture variance sequence, m (is one element of a set M) is random variables of degree of freedom of a model structure, and [q(, Z|O, m)] is posteriori distributions of the variational Bayes method. m is fixed to obtain q(_c|O, m) and q(Z|O, m), and these are used to obtain an F^m value, and q(_c|O, m) and q(Z|O, m) which maximize the F^m value are obtained. A model structure is determined by obtaining m in the set M, which maximizes F^m[q(, Z|O, m)].;COPYRIGHT: (C)2004,JPO