Using Vector Quantization for Universal Background Model in Automatic Speaker Verification
Hayet Djellali, Laskri Mohamed Tayeb, Badji Mokhtar · 2012
Abstract. We aim to describe different approaches for vector quantization in Automatic Speaker Verification. We designed our novel architecture based on multiples codebook representing the speakers and the impostor model called universal background model and compared it to another vector quantization approach used for reducing training data. We compared our scheme with the baseline system, Gaussian Mixtures Models and Maximum a Posteriori Adaptation. The present study demonstrates that the multiples codebook gives more verification accuracy called equal error rate but this improvement also depends on the codebook size.