Emirati Speaker Verification Based on HMM1s, HMM2s, and HMM3s

TL;DR

This paper evaluates the effectiveness of first, second, and third-order Hidden Markov Models for Emirati speaker verification, demonstrating that higher-order models significantly improve accuracy in neutral talking environments.

Contribution

It introduces a comparative analysis of HMM1s, HMM2s, and HMM3s specifically for Emirati speaker verification using a new speech database.

Findings

HMM3s outperform HMM1s and HMM2s in accuracy

Results with HMM3s are close to human subjective assessment

The study provides a benchmark for Emirati speaker verification

Abstract

This work focuses on Emirati speaker verification systems in neutral talking environments based on each of First-Order Hidden Markov Models (HMM1s), Second-Order Hidden Markov Models (HMM2s), and Third-Order Hidden Markov Models (HMM3s) as classifiers. These systems have been evaluated on our collected Emirati speech database which is comprised of 25 male and 25 female Emirati speakers using Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features. Our results show that HMM3s outperform each of HMM1s and HMM2s for a text-independent Emirati speaker verification. The obtained results based on HMM3s are close to those achieved in subjective assessment by human listeners.