Emirati-Accented Speaker Identification in each of Neutral and Shouted Talking Environments

TL;DR

This study develops and evaluates circular suprasegmental Hidden Markov Models for Emirati-accented speaker identification in neutral and shouted environments, achieving high accuracy in neutral and moderate accuracy in shouted conditions.

Contribution

It introduces a new Emirati-accented speech database and compares the effectiveness of CSPHMMs of different orders for speaker identification in challenging shouted environments.

Findings

High identification accuracy in neutral environment (up to 95.9%)

Moderate accuracy in shouted environment (up to 59.3%)

CSPHMM3s outperform lower-order models in shouted conditions

Abstract

This work is devoted to capturing Emirati-accented speech database (Arabic United Arab Emirates database) in each of neutral and shouted talking environments in order to study and enhance text-independent Emirati-accented speaker identification performance in shouted environment based on each of First-Order Circular Suprasegmental Hidden Markov Models (CSPHMM1s), Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s), and Third-Order Circular Suprasegmental Hidden Markov Models (CSPHMM3s) as classifiers. In this research, our database was collected from fifty Emirati native speakers (twenty five per gender) uttering eight common Emirati sentences in each of neutral and shouted talking environments. The extracted features of our collected database are called Mel-Frequency Cepstral Coefficients (MFCCs). Our results show that average Emirati-accented speaker identification performance in neutral environment is 94.0%, 95.2%, and 95.9% based on CSPHMM1s, CSPHMM2s, and CSPHMM3s, respectively. On the other hand, the average performance in shouted environment is 51.3%, 55.5%, and 59.3% based, respectively, on CSPHMM1s, CSPHMM2s, and CSPHMM3s. The achieved average speaker identification performance in shouted environment based on CSPHMM3s is very similar to that obtained in subjective assessment by human listeners.