Seamless: Multilingual Expressive and Streaming Speech Translation
Large-scale automatic speech translation systems today lack key features that help machine-
mediated communication feel seamless when compared to human-to-human dialogue. In …
mediated communication feel seamless when compared to human-to-human dialogue. In …
Wavmark: Watermarking for audio generation
Recent breakthroughs in zero-shot voice synthesis have enabled imitating a speaker's voice
using just a few seconds of recording while maintaining a high level of realism. Alongside its …
using just a few seconds of recording while maintaining a high level of realism. Alongside its …
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 …
impersonate voices. Audio watermarking can combat misuse by embedding a traceable …
DRAW: Dual-decoder-based Robust Audio Watermarking Against Desynchronization and Replay Attacks
Digital watermarking is a widely adopted authentication technique and one of its primary
concerns in practical usage is robustness. However, existing audio watermarking methods …
concerns in practical usage is robustness. However, existing audio watermarking methods …
HiFi-GANw: Watermarked Speech Synthesis Via Fine-Tuning of HiFi-GAN
X Cheng, Y Wang, C Liu, D Hu… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
Advancements in speech synthesis technology bring generated speech closer to natural
human voices, but they also introduce a series of potential risks, such as the dissemination …
human voices, but they also introduce a series of potential risks, such as the dissemination …
[HTML][HTML] An Audio Watermarking Algorithm Based on Adversarial Perturbation
S Wu, J Liu, Y Huang, H Guan, S Zhang - Applied Sciences, 2024 - mdpi.com
Recently, deep learning has been gradually applied to digital watermarking, which avoids
the trouble of hand-designing robust transforms in traditional algorithms. However, most of …
the trouble of hand-designing robust transforms in traditional algorithms. However, most of …
Hybrid deep learning based digital image watermarking using GAN-LSTM and adaptive gannet optimization techniques
SM Shedole, V Santhi - Multimedia Tools and Applications, 2024 - Springer
Nowadays, multimedia technology is progressing everyday. It is very easy to duplicate,
distribute and modify digital images with online editing software. Image security and privacy …
distribute and modify digital images with online editing software. Image security and privacy …
Latent Watermarking of Audio Generative Models
The advancements in audio generative models have opened up new challenges in their
responsible disclosure and the detection of their misuse. In response, we introduce a …
responsible disclosure and the detection of their misuse. In response, we introduce a …
TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking
Various threats posed by the progress in text-to-speech (TTS) have prompted the need to
reliably trace synthesized speech. However, contemporary approaches to this task involve …
reliably trace synthesized speech. However, contemporary approaches to this task involve …
[PDF][PDF] Detecting Voice Cloning Attacks via Timbre Watermarking
Nowadays, it is common to release audio content to the public, for social sharing or
commercial purposes. However, with the rise of voice cloning technology, attackers have the …
commercial purposes. However, with the rise of voice cloning technology, attackers have the …