Application of Improved Spectral Subtraction Algorithm for Speech Emotion Recognition

摘要

The information extraction and recognition of speech emotional information under the noise environment has been the research hotspot and difficulty, which limits the application of speech emotion recognition technology. An improved spectral subtraction algorithm is presented based on the analysis on the basic principle of spectral subtraction. According to the distribution of noise, the improved algorithm estimates precisely the amplitude of noise. The improved spectral subtraction algorithm used in signal processing of speech emotion recognition can eliminate background noise. Experiments show that feature extraction used the improved spectral subtraction algorithm can better reflect the speech emotional information, and compared with traditional ways, the speech emotion recognition system get good robustness and recognition performance.