Recognition of two words Chinese lexical for non-specific people using feature fusion of broadband and narrowband spectrogram

This paper presents a recognition method to two words Chinese lexical for non-specific people using feature fusion of broadband and narrow-band spectrogram. In the process of image feature extraction, the image processing technique is applicable to the speech recognition field. First, equal width zoning line projection and binary width zoning line projection is carried out in the narrow-band spectrogram, sets respectively as the narrow-band spectrogram of the first character set and the second character set. Meanwhile, equal width zoning line projection is carried out again in the narrowband spectrogram after Fourier transforms, treating it as the third feature set. Then, equal width column projection is carried out in the broadband spectrogram, regarding it as the fourth feature set. The above four feature sets are used as the feature vectors for support vector machine (SVM) as a classifier to the overall recognition of two words Chinese lexical for non-specific people. A total of 1000 voice samples are used in the simulation experiment. The correct recognition rate of two words Chinese lexical recognition by using the feature value fusion of the above four features can reach 93.6 percent, this method of feature fusion provides a new way of thinking of Chinese vocabulary overall recognition.