A New Hybrid GMM/SVM for Speaker Verification

Citations Over TimeTop 10% of 2006 papers

Abstract

This paper proposes a new combination approach between Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) by feature extraction based on adapted GMM for SVM in text-independent speaker verification. Because of excellent scalability, adapted GMM was used to extract a small quantity of typical feature vectors from large numbers of speech data for SVM speaker verification. Using this new combination approach, our speaker verification system performed significantly better than the current state-of-the-art GMM-UBM system on the NIST'04 1side-1side database.

Related Papers

• → Fused Mel Feature sets based Text-Independent Speaker Identification using Gaussian Mixture Model(2012)31 cited
• → An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization(2010)30 cited
• Individuality Music Recommendation Model Based on MFCC and GMM(2009)
• → Speaker Recognition and Diarization(2010)3 cited
• → A supplementary feature for speaker verification in constrained room acoustics(2005)