Dynamic segmental vector quantization in isolated-word speech recognition

The standard Vector Quantization (VQ) approach that uses a single vector quantizer for each entire duration of the utterance of each class suffers from the following two limitations: 1) high computational cost for large codehook sizes and 2) lack of explicit characterization of the sequential behavior. Both of two these disadvantages can be remedied by treating each utterance class as a concatenation of several information sub-sources, each of which is represented by a VQ codebook. With this approach, segmentation schemes obviously need to be investigated. And we call this VQ approach Dynamic Segmental Vector Quantization (DSVQ). This paper shows how to design DSVQ with some effective segmentation schemes. Better performances could be seen when applying this approach itself or mixed with Hidden Markov Model (HMM) in isolated-word speech recognition.