Speech recognition system based on DSP and SVM

Speech recognition can achieve a simple human-computer interaction and voice control. It is widely used in industrial control, consumer electronics and many other fields. Combining with the characteristic of human physiology, the paper presents a higher-performance speech recognition system for specific people and isolated words. It realizes on a DSP (Digital Signal Processor)system by using the LPMCC (Linear Prediction Coefficient and Mel-Frequency Cepstral Coefficient) as the feature vector and dynamic programming algorithm as the core algorithm. The SVM (Support Vector Machine) have become a popular tool for machine learning task in the system to modify the real-time processing efficiency.