EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion
Paper
•
2412.20359
•
Published
•
8
•
1
Shah Nirmesh
Nirmesh
·
AI & ML interests
Speech Processing
Recent Activity
liked
a model
about 2 months ago
DiscreteSpeech/DSTK
upvoted
a
paper
2 months ago
In-Domain African Languages Translation Using LLMs and Multi-armed
Bandits
Organizations
None yet
commented
4
papers
2 months ago
VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech
Paper
•
2406.08076
•
Published
•
6
•
1
DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing
Paper
•
2406.08802
•
Published
•
8
•
1
REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion
Paper
•
2505.20756
•
Published
•
8
•
1