Maskmark: Robust Neuralwatermarking for Real and Synthetic Speech

High-quality speech synthesis models may be used to spread misinformation or impersonate voices. Audio watermarking can combat misuse by embedding a traceable signature in generated audio. However, existing audio watermarks typically demonstrate robustness to only a small set of transformations of t...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 4650 - 4654
Main Authors O'Reilly, Patrick, Jin, Zeyu, Su, Jiaqi, Pardo, Bryan
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.04.2024
Subjects
Codecs
Detectors
Robustness
speech synthesis
synthetic media
Training
Vectors
Vocoders
Watermarking
Online AccessGet full text

Cover

More Information
Summary:High-quality speech synthesis models may be used to spread misinformation or impersonate voices. Audio watermarking can combat misuse by embedding a traceable signature in generated audio. However, existing audio watermarks typically demonstrate robustness to only a small set of transformations of the watermarked audio. To address this, we propose MaskMark, a neural network-based digital audio watermarking technique optimized for speech. MaskMark embeds a secret key vector in audio via a multiplicative spectrogram mask, allowing the detection of watermarked speech segments even under substantial signal-processing or neural network-based transformations. Comparisons to a state-of-the-art baseline on natural and synthetic speech corpora and a human subjects evaluation demonstrate MaskMark's superior robustness in detecting watermarked speech while maintaining high perceptual transparency.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447253