Quantile Acoustic Vectors vs. MFCC Applied to Speaker Verification. (18th February 2014)

• Record Type: Journal Article
• Authors: Pedro, Mayorga-Ortiz; Martín, Olguín-Espinoza J.; Hugo, González-Arriaga O.; Flores, Nylsa; Luis, Vizcarra-Corral
• Is Part Of: International journal of advanced robotic systems. Volume 11:Number 2(2014)
• Publication Date: 2014-02-18
• Subjects: Quantile Vectors -- Gaussian Mixture Models (GMM) -- Speaker Verification; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.5772/56256
• Languages: English
• ISSNs: 1729-8806

Abstract

In this paper we describe speaker and command recognition related experiments, through quantile vectors and Gaussian Mixture Modelling (GMM). Over the past several years GMM and MFCC have become two of the dominant approaches for modelling speaker and speech recognition applications. However, memory and computational costs are important drawbacks, because autonomous systems suffer processing and power consumption constraints; thus, having a good trade-off between accuracy and computational requirements is mandatory. We decided to explore another approach (quantile vectors in several tasks) and a comparison with MFCC was made. Quantile acoustic vectors are proposed for speaker verification and command recognition tasks and the results showed very good recognition efficiency. This method offered a good trade-off between computation times, characteristics vector complexity and overall achieved efficiency.