Endpoint detection algorithm for Mandarin Digit Recognition using DSP

When Mandarin Digit Speech Recognition (MDSR) is applied to adverse environment, endpoint detection can be crucial to the entire system. A novel Feature-based Real-time Endpoint Detection (FRED) algorithm is proposed in this paper. In later experiment, the proposed algorithm is shown to be more accurate and-noise robust than previously proposed approaches. FRED detects speech endpoint depending on the essential speech feature, which makes the system has high disturbance-proof ability. The feature used for endpoint detection can be figured out conveniently when computing Mel-Frequency Cepstral Coefficients (MFCC); furthermore, the algorithm has a low complexity and is suitable for real-time DSP system. FRED algorithm is able to segment vowel and consonant reliably, which makes it possible to further recognize by local feature to improve system performance.