Detection of AI Synthesized Hindi Speech

TL;DR

This paper presents a highly accurate method for detecting AI-generated Hindi speech using machine learning and deep neural networks, addressing a gap in audio forensics for non-English languages.

Contribution

It introduces a novel approach utilizing specific acoustic features and deep neural networks for synthetic Hindi speech detection, achieving near-perfect accuracy.

Findings

VGG16 achieved 99.83% accuracy.

Homemade CNN achieved 99.99% accuracy.

Features like Bicoherence and MFCC are effective for detection.

Abstract

The recent advancements in generative artificial speech models have made possible the generation of highly realistic speech signals. At first, it seems exciting to obtain these artificially synthesized signals such as speech clones or deep fakes but if left unchecked, it may lead us to digital dystopia. One of the primary focus in audio forensics is validating the authenticity of a speech. Though some solutions are proposed for English speeches but the detection of synthetic Hindi speeches have not gained much attention. Here, we propose an approach for discrimination of AI synthesized Hindi speech from an actual human speech. We have exploited the Bicoherence Phase, Bicoherence Magnitude, Mel Frequency Cepstral Coefficient (MFCC), Delta Cepstral, and Delta Square Cepstral as the discriminating features for machine learning models. Also, we extend the study to using deep neural networks for extensive experiments, specifically VGG16 and homemade CNN as the architecture models. We obtained an accuracy of 99.83% with VGG16 and 99.99% with homemade CNN models.