Text Independent Speaker Recognition and Speaker Independent Speech Recognition Using Iterative Clustering Approach

This paper presents the effectiveness of perceptual features and iterative clustering approach for performing both speech and speaker recognition. Procedure used for formation of training speech is different for developing training models for speaker independent speech and text independent speaker recognition. So, this work mainly emphasizes the utilization of clustering models developed for the training data to obtain better accuracy as 91%, 91% and 99.5% for mel frequency perceptual linear predictive cepstrum with respect to three categories such as speaker identification, isolated digit recognition and continuous speech recognition. This feature also produces 9% as low equal error rate which is used as a performance measure for speaker verification. The work is experimentally evaluated on the set of isolated digits and continuous speeches from TI digits_1 and TI digits_2 database for speech recognition and on speeches of 50 speakers randomly chosen from TIMIT database for speaker recognition. The noteworthy feature of speaker recognition algorithm is to evaluate the testing procedure on identical messages of all the 50 speakers, theoretical validation of results using F-ratio and validation of results by statistical analysis using χ² distribution.