Dynamic Time Warping Based Approach to Text-Dependent Speaker Identification Using Spectrograms

The goal of this paper is to study a new approach to text dependent speaker identification using the complex patterns of variation in frequency and amplitude with time while an individual utters a given word through spectrogram segmentation and template matching. The optimally segmented spectrograms are used as a database to successfully identify the unknown individual from his/her voice. The methodology used for identifying, rely on classification of spectrograms (of speech signals), based on dynamic time warping (DTW) matching of conditionally quantized frequency-time domain features of the database samples and the unknown speech sample. Experimental results on a sample collected from 40 speakers show that this methodology can be effectively used to produce a desirable success rate.