Synthetic Speech Detection Based On Temporal Consistency And Distribution Of Speaker Features
2023 · Yuxiang Zhang, Zhuo Li, Jingze Lu, et al.
Abstract
Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this paper, the flaws of the speaker features inherent in the text-to-speech (TTS) process are analyzed. Differences in the temporal consistency of intra-utterance speaker features arise due to the lack of fine-grained control over speaker features in TTS. Since the speaker representations in TTS are based on speaker embeddings extracted by encoders, the distribution of inter-utterance speaker features differs between synthetic and bonafide speech. Based on these analyzes, an SSD method based on temporal consistency and distribution of speaker features is proposed. On one hand, modeling the temporal consistency of intra-utterance speaker features can aid speech anti-spoofing. On the other hand, distribution differences in inter-utterance speaker features
Authors
(none)
Tags
Stats
Related papers
- Dual-branch Knowledge Distillation For Noise-robust Synthetic Speech Detection (2023)9.07
- Speech-forensics: Towards Comprehensive Synthetic Speech Dataset Establishment And Analysis (2024)3.58
- Robust Ai-synthesized Speech Detection Using Feature Decomposition Learning And Synthesizer Feature Augmentation (2024)8.35
- Evaluating And Reducing The Distance Between Synthetic And Real Speech Distributions (2022)0.00
- Open Challenges In Synthetic Speech Detection (2022)10.97
- Combining Automatic Speaker Verification And Prosody Analysis For Synthetic Speech Detection (2022)10.48
- Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
- Lightweight Model Attribution And Detection Of Synthetic Speech Via Audio Residual Fingerprints (2024)0.00