Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram

This paper illustrates a method to recognize nonspecific two-word Chinese vocabulary by analyzing speech signals using a narrow-band spectrogram after Fourier transform is applied to it twice. Binary width zoning line projection is carried out in the frequency domain. The projection value is treated as the characteristic value of semantic recognition feature and the support vector machine (SVM) is considered as the classifier for recognizing the semantics of non-specific two-word Chinese vocabulary. A total of 1000 voice samples were used in the simulation. The results using this method show a remarkable recognition rate of 96.0%.The proposed method provides a new way for vocabulary recognition.

[1]  Michael Riley,et al.  Schematizing spectrograms for speech recognition , 1983 .

[2]  Chidchanok Lursinsap,et al.  Singing voice recognition based on matching of spectrogram pattern , 2009, 2009 International Joint Conference on Neural Networks.

[3]  Mathew J. Palakal,et al.  Feature extraction from speech spectrograms using multi-layered network models , 1989, [Proceedings 1989] IEEE International Workshop on Tools for Artificial Intelligence.

[4]  Xu Zhao,et al.  A Mathematical Morphological Processing of Spectrograms for the Tone of Chinese Vowels Recognition , 2014 .

[5]  Steven Greenberg,et al.  The modulation spectrogram: in pursuit of an invariant representation of speech , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Ben Pinkowski.  Principal component analysis of speech spectrogram images , 1997, Pattern Recognit..

[7]  Xueying Zhang,et al.  Evaluation of a set of new ORF kernel functions of SVM for speech recognition , 2013, Eng. Appl. Artif. Intell..

[8]  M. Bodruzzaman,et al.  Speech recognition using pulse coupled neural network , 1998, Proceedings of Thirtieth Southeastern Symposium on System Theory.