An HMM-MLP hybrid approach for improving discrimination in speech recognition

Abstract

In this paper, we propose an HMMZMLP hybrid scheme for achieving high discrimination in speech recognition. Io the conventional hybrid approaches, an MLP is trained as a distribution estimator or as a VQ labeler, and the HMMs pegonn recognition using the output of the MLP, In the proposed method, to the contrary, HMMs generate a new feature vector of a fixed dimension by concatenating their state log-likelihoods, and an MLP discriminator pegoms recognition by using this new feature vector as an input. The proposed method was tested on the nine American E-set letters from the ISOLET database of the OGI. For comparison, a weighted HMM VHMM) algorithm and GPD-based WHMM algorithm which use an adaptively-trained linear discriminator were also tested. In most cases, the recognition rates on the closed-test and open-test sets of the proposed method were higher than those of the conventional methods.