Speaker recognition is one of the major fields of research which deals with recognizing the speaker, having applications mainly in authentication purposes. The paper presents a simple full distance matrix feature matching technique besides frame optimization as pre-processing stage in feature extraction module. The results in the last section show that the performance is better than that of the existing algorithms which use complex feature matching techniques.
Keywords
Cepstral Coefficients, Full Distance Matrix, Mel Frequency, Mel Filters, Speaker Recognition
User
Information