The cascade HMM/ANN hybrid: A new framework for discriminative training in speech recognition.
Iman Gholampour, K. Nayebi · NSIP · 1999
In this paper, a new formulation for discriminative training of HMMs is presented. This formulation uses a properly trained MLP in a simple interconnection with HMMs called “Cascade HMM/ANN Hybrid”. Our training algorithm has simple realization in comparison with other discriminative training for HMMs such as MDI and MMI. We also present a rigid mathematical proof of its convergence. We found that using cascade HMM/ANN for isolated word recognition in noisy environment results in increasing the recognition accuracy from 93.3% in classic HMMs to 99.1% using a two layer MLP. No significant increase in computational requirements is needed in recognition phase. Both theoretical and experimental achievements are included in the paper.