Descriptor:: Extended-Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition (ELAD-SVDSR)

View on arXiv ← Back to list

Authors: Rahul Vijaykumar, Ajan Ahmed, John Parker, Dinesh Pendyala, Aidan Collins, Stephanie Schuckers, Masudul H. Imtiaz

Published: 2025-09-30 19:46:50+00:00

AI Summary

This paper introduces ELAD-SVDSR, a novel extended-length audio dataset designed for synthetic voice detection and speaker recognition. It comprises 45-minute audio recordings from 36 participants, captured with five different microphones, along with 20 generated deepfake voices. The dataset aims to facilitate the creation of high-quality deepfakes and the development of robust detection systems.

Abstract

This paper introduces the Extended Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition (ELAD SVDSR), a resource specifically designed to facilitate the creation of high quality deepfakes and support the development of detection systems trained against them. The dataset comprises 45 minute audio recordings from 36 participants, each reading various newspaper articles recorded under controlled conditions and captured via five microphones of differing quality. By focusing on extended duration audio, ELAD SVDSR captures a richer range of speech attributes such as pitch contours, intonation patterns, and nuanced delivery enabling models to generate more realistic and coherent synthetic voices. In turn, this approach allows for the creation of robust deepfakes that can serve as challenging examples in datasets used to train and evaluate synthetic voice detection methods. As part of this effort, 20 deepfake voices have already been created and added to the dataset to showcase its potential. Anonymized metadata accompanies the dataset on speaker demographics. ELAD SVDSR is expected to spur significant advancements in audio forensics, biometric security, and voice authentication systems.

Key findings

The ELAD-SVDSR dataset provides extended-duration audio (45 min/speaker) from 36 participants with diverse demographics, recorded via five distinct microphones, and includes 20 deepfake voices. The dataset exhibits high signal-to-noise ratios (mean 57.41 dB), ensuring high-quality recordings. The generated deepfakes show higher normalized VeriSpeak match scores (37.2%) compared to deepfakes created from other common speech datasets, indicating their potential as challenging examples for detection.

Approach

The authors created a new dataset by recording 36 participants reading newspaper articles for 45 minutes each, using five different microphones under controlled conditions. They then preprocessed this data and generated 20 deepfake voices using Tortoise TTS, which were included in the dataset, along with anonymized speaker demographics.

Datasets

ELAD-SVDSR (Extended-Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition)

Model(s)

UNKNOWN

Author countries

USA

← Previous