Researchers aim to create sounds that match silent videos, improving viewer experiences.
― 5 min read
Yong Ren
A novel approach improves detection of mixed real and fake audio clips.
― 6 min read
Introducing SpikeVoice, an energy-efficient system for high-quality text-to-speech synthesis.
― 5 min read
DAC model improves audio captioning with speed and diversity.
― 5 min read
WMCodec enhances audio watermarking for better security and authenticity.
― 5 min read
A new method boosts AUV performance in underwater tracking tasks.
― 9 min read
New method improves detection of audio deepfakes using innovative learning techniques.
― 6 min read