跳到主要导航 跳到搜索 跳到主要内容

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

  • Xi'an Jiaotong University
  • Hong Kong Polytechnic University

科研成果: 书/报告/会议事项章节会议稿件同行评审

6 引用 (Scopus)

摘要

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.

源语言英语
主期刊名Proceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
编辑Kate Larson
出版商International Joint Conferences on Artificial Intelligence
413-421
页数9
ISBN(电子版)9781956792041
出版状态已出版 - 2024
活动33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 - Jeju, 韩国
期限: 3 8月 20249 8月 2024

出版系列

姓名IJCAI International Joint Conference on Artificial Intelligence
ISSN(印刷版)1045-0823

会议

会议33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
国家/地区韩国
Jeju
时期3/08/249/08/24

学术指纹

探究 'Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis' 的科研主题。它们共同构成独一无二的指纹。

引用此