Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Zhoulin, Lin, Chenhao, Wang, Hang, Shen, Chao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915394312208384
author Ji, Zhoulin
Lin, Chenhao
Wang, Hang
Shen, Chao
author_facet Ji, Zhoulin
Lin, Chenhao
Wang, Hang
Shen, Chao
contents Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas, limiting their utility for comprehensive research. To fill this gap, we propose the Speech-Forensics dataset by extensively covering authentic, synthetic, and partially forged speech samples that include multiple segments synthesized by different high-quality algorithms. Moreover, we propose a TEmporal Speech LocalizaTion network, called TEST, aiming at simultaneously performing authenticity detection, multiple fake segments localization, and synthesis algorithms recognition, without any complex post-processing. TEST effectively integrates LSTM and Transformer to extract more powerful temporal speech representations and utilizes dense prediction on multi-scale pyramid features to estimate the synthetic spans. Our model achieves an average mAP of 83.55% and an EER of 5.25% at the utterance level. At the segment level, it attains an EER of 1.07% and a 92.19% F1 score. These results highlight the model's robust capability for a comprehensive analysis of synthetic speech, offering a promising avenue for future research and practical applications in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09032
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis
Ji, Zhoulin
Lin, Chenhao
Wang, Hang
Shen, Chao
Sound
Artificial Intelligence
Audio and Speech Processing
Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas, limiting their utility for comprehensive research. To fill this gap, we propose the Speech-Forensics dataset by extensively covering authentic, synthetic, and partially forged speech samples that include multiple segments synthesized by different high-quality algorithms. Moreover, we propose a TEmporal Speech LocalizaTion network, called TEST, aiming at simultaneously performing authenticity detection, multiple fake segments localization, and synthesis algorithms recognition, without any complex post-processing. TEST effectively integrates LSTM and Transformer to extract more powerful temporal speech representations and utilizes dense prediction on multi-scale pyramid features to estimate the synthetic spans. Our model achieves an average mAP of 83.55% and an EER of 5.25% at the utterance level. At the segment level, it attains an EER of 1.07% and a 92.19% F1 score. These results highlight the model's robust capability for a comprehensive analysis of synthetic speech, offering a promising avenue for future research and practical applications in this field.
title Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2412.09032