A comparison between HMM and hybrid ANN-HMM-based systems for continuous speech recognition

摘要

The purpose of this paper is to compare the performance of two continuous speech recognition systems, one based on hidden Markov models (HMM) and the other based on hybrid artificial neural networks and hidden Markov models (ANN-HMM). The comparisons are in terms of recognition rate and in terms of computational complexity. Preliminary results points favorably to hybrid systems.