2 papers
cs.CL2025
Improving French Synthetic Speech Quality via SSML Prosody Control
Nassima Ould Ouali, Awais Hussain Sani, Ruben Bueno +3
Despite recent advances, synthetic voices often lack expressiveness due to limited prosody control in commercial text-to-speech (TTS) systems. We introduce the first end-to-end pip…
cs.CV2025
FakeParts: a New Family of AI-Generated DeepFakes
Ziyi Liu, Firas Gabetni, Awais Hussain Sani +5
We introduce FakeParts, a new class of deepfakes characterized by subtle, localized manipulations to specific spatial regions or temporal segments of otherwise authentic videos. Un…