Speech Recognition System Based on Integrating Feature and HMM

Automatic speech processing systems are employed more and more often in real environments. However, they are confronted with high ambient noise levels and their performance degrades drastically. An robust and practical speech recognition system using integrating feature and Hidden Markov Model(HMM) was proposed aiming at improving speech recognition rate in noise environmental conditions. It integrated different speech features into the system, based on global optimization, a new Genetic Algorithm(GA) for training HMM was proposed. The system is comprised of three main sections, a pre-processing section, a feature extracting section and a HMM processing section. Six chinese vowels were taken as the experimental data. Recognition experiments show that the method is effective and high speed and accuracy for speech recognition.