Novel Cascaded Gaussian Mixture Model-Deep Neural Network Classifier for Speaker Identification in Emotional Talking Environments

TL;DR

This paper introduces a novel cascaded Gaussian Mixture Model-Deep Neural Network classifier that significantly improves speaker identification accuracy in emotional talking environments, outperforming traditional classifiers across multiple speech datasets.

Contribution

The study proposes and evaluates a new cascaded GMM-DNN classifier specifically designed for speaker identification in emotional speech, demonstrating superior performance over classical methods.

Findings

Cascaded GMM-DNN outperforms MLP and SVM classifiers.

Improved speaker identification accuracy across emotional speech datasets.

Performance comparable to human subjective assessment.

Abstract

This research is an effort to present an effective approach to enhance text-independent speaker identification performance in emotional talking environments based on novel classifier called cascaded Gaussian Mixture Model-Deep Neural Network (GMM-DNN). Our current work focuses on proposing, implementing and evaluating a new approach for speaker identification in emotional talking environments based on cascaded Gaussian Mixture Model-Deep Neural Network as a classifier. The results point out that the cascaded GMM-DNN classifier improves speaker identification performance at various emotions using two distinct speech databases: Emirati speech database (Arabic United Arab Emirates dataset) and Speech Under Simulated and Actual Stress (SUSAS) English dataset. The proposed classifier outperforms classical classifiers such as Multilayer Perceptron (MLP) and Support Vector Machine (SVM) in each dataset. Speaker identification performance that has been attained based on the cascaded GMM-DNN is similar to that acquired from subjective assessment by human listeners.