A weighted distance measure based on the fine structure of feature space: application to speaker recognition

A weighted cepstral distance measure is proposed and tested in a speaker recognition system using a speaker-based vector quantization (VQ) approach. Based on the fine structure of the feature vector space, a statistically optimized distance measure is defined with weights equal to the partition-normalized inverse variance of cepstral coefficients. The weights can be adjusted individually for each partition and each component of the feature vector across all codebooks (speakers). Experiments on a 50-speaker database show that the suggested weighted cepstral distance measure works substantially better than the Euclidean cepstral distance or the inverse variance weighted cepstral distance. An accuracy of about 90% is achieved using a 16-level codebook in speaker verification