Improving speaker verification robustness with synthetic emotional utterances

TL;DR

This paper introduces a CycleGAN-based data augmentation method to generate synthetic emotional speech, enhancing speaker verification systems' robustness across emotional states and reducing error rates.

Contribution

The study presents a novel use of CycleGAN for synthesizing emotional speech data, improving speaker verification accuracy in emotional scenarios.

Findings

Synthetic emotional data improves verification accuracy

Reduced equal error rate by up to 3.64%

Enhanced robustness across emotional speech variations

Abstract

A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker. This technology has paved the way for various personalized applications that cater to individual preferences. A noteworthy challenge faced by SV systems is their ability to perform consistently across a range of emotional spectra. Most existing models exhibit high error rates when dealing with emotional utterances compared to neutral ones. Consequently, this phenomenon often leads to missing out on speech of interest. This issue primarily stems from the limited availability of labeled emotional speech data, impeding the development of robust speaker representations that encompass diverse emotional states. To address this concern, we propose a novel approach employing the CycleGAN framework to serve as a data augmentation method. This technique synthesizes emotional speech segments for each specific speaker while preserving the unique vocal identity. Our experimental findings underscore the effectiveness of incorporating synthetic emotional data into the training process. The models trained using this augmented dataset consistently outperform the baseline models on the task of verifying speakers in emotional speech scenarios, reducing equal error rate by as much as 3.64% relative.