Performance Comparison Of 2-D DCT On Full/Block Spectrogram And 1-D DCT On Row Mean Of Spectrogram For Speaker Identification

The goal of this paper is to present a very simple approach to text dependent speaker identification using a combination of spectrograms and well known Discrete Cosine Transform (DCT). This approach is based on use of DCT to find similarities between spectrograms obtained from speech samples. The set of spectrograms forms the database for our experiments rather than raw speech samples. Performance of this approach is compared for different number of coefficients of DCT when DCT is applied on entire spectrogram, when DCT is applied to spectrogram divided into blocks and when DCT is applied to the Row Mean of a spectrogram. Performance comparison shows that, number of mathematical computations required for DCT on Row Mean of spectrogram method is drastically less as compared to other two methods with almost equal identification rate.