Vowel based Speaker Verification using Self Organising Map

Tariq Tashan, Tony Allen, and Lars Nolle


Speaker verification, Self organising map, DFT


A vowel-dependent speaker verification system that uses a modified Self Organising Map (SOM) algorithm is presented. For each speaker, a seeded SOM is trained to produce representative Discrete Fourier Transform (DFT) vectors of three vowels of a spoken input. This SOM training is performed both during a registration phase and during each subsequent verification attempt. Speaker verification is achieved by computing the Euclidean distance between the registration and verification SOM trained weight sets. An analysis of the comparative system performance when using Linear Prediction Code (LPC) spectrum and Mel Frequency Cepstrum Coefficients (MFCC) as alternative input features is given. The algorithm was evaluated using 50 speakers from the Center for Spoken Language Understanding (CSLU2002) speaker verification database.

Important Links:

Go Back