A Speech Recognizer based on Multiclass SVMs with HMM-Guided Segmentation

Abstract

Automatic Speech Recognition (ASR) is essentially a problem of pattern classification, however, the time dimension of the speech signal has prevented to pose ASR as a simple static classification problem. Support Vector Machine (SVM) classifiers could provide an appropriate solution, since they are very well adapted to high-dimensional classification problems. Nevertheless, the use of SVMs for ASR is by no means straightforward, mainly because SVM classifiers require an input of fixed-dimension. In this paper we study the use of a HMM-based segmentation as a mean to get the fixed-dimension input vectors required by SVMs, in a problem of isolated-digit recognition. Different configurations for all the parameters involved have been tested. Also, we deal with the problem of multi-class classification (as SVMs are initially binary classifers), studying two of the most popular approaches: 1-vs-all and 1-vs-1.