作者: JS Pan , FR McInnes , MA Jack , None
关键词:
摘要: A bound for a Minkowski metric based on L/sub p/ distortion measure is proposed and evaluated as means to reduce the computation in vector quantisation. This provides better criterion than absolute error inequality (AEI) elimination rule Euclidean measure. For of order n, this contributes from 1/ n/ metric. can also be an extended quadratic which hidden Markov model (HMM) with Gaussian mixture probability density function (PDF). In speech recognition, HMM VQ codebook PDF has been shown promising method.