#synthetic-speech News & Analysis

6 articles tagged with #synthetic-speech. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

6 articles

AIBearisharXiv – CS AI · Jun 237/10

🧠

The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection

Researchers discovered that audio deepfake detectors trained on watermarked synthetic speech and unwatermarked real speech exploit watermarks as a spurious shortcut, causing three critical failures: poor generalization, watermarked fakes evading detection, and real watermarked speech being flagged as fake. The vulnerability affects commercial platforms like ElevenLabs and AudioSeal, though retraining detectors with watermarks on both classes resolves the issue.

AINeutralarXiv – CS AI · May 287/10

🧠

I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors

Researchers conducted a study with 47 participants to evaluate how humans detect synthetic speech, testing detection accuracy across authentic, fully synthetic, and partially synthetic utterances under various trust manipulation conditions. The findings reveal that humans perform poorly at detecting fully synthetic speech (below-chance levels) and that trust cues like instructional framing and provenance labeling do not significantly improve detection, though they influence detection behavior.

AIBearisharXiv – CS AI · May 287/10

🧠

Voice "Cloning" is Style Transfer

Research reveals that voice cloning technology doesn't faithfully replicate voices but instead applies systematic style transfer, making cloned voices sound more authoritative and trustworthy than originals. The findings expose significant limitations in current voice cloning models, including homogenization of speaker characteristics and potential risks related to human behavioral manipulation through altered voice perception.

AIBullisharXiv – CS AI · Jun 196/10

🧠

FlowFake: Liquid Networks for Audio Deepfake Detection

Researchers introduce FlowFake, a lightweight neural architecture using Liquid Time-Constant networks to detect audio deepfakes with superior cross-dataset generalization. The model achieves comparable performance to much larger systems while addressing the critical challenge of detecting synthetic speech artifacts across different synthesis pipelines with only 34K parameters.

$LTC

AINeutralarXiv – CS AI · Jun 106/10

🧠

Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing

Researchers propose a dual-branch gated fusion framework to identify the source of synthetic audio deepfakes, combining XLSR-53 with CORES descriptors to achieve 97.6% accuracy on in-domain tests and superior generalization to unseen synthesizers. The approach addresses a critical security gap where existing closed-set models fail to reject unknown audio generation systems.

AINeutralarXiv – CS AI · Jun 106/10

🧠

What Do Deepfake Speech Detectors Actually Hear?

Researchers developed an explainability pipeline that reveals what deepfake speech detectors actually focus on when identifying synthetic audio. The study found that three leading WavLM-based detectors rely on fundamentally different cues—environmental artifacts, phoneme distortions, and spectral patterns—despite achieving similar accuracy levels, with findings validated through causal masking experiments.