Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
Paper
•
2404.19622
•
Published
•
2
Shivam Mehta
shivammehta25
AI & ML interests
Speech, Audio, LLM, Flow Matching, Diffusion, Flows, HMMs
Organizations
authored
a
paper
over 1 year ago
authored
6
papers
almost 2 years ago
Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation
Paper
•
2309.05455
•
Published
Prosody-controllable spontaneous TTS with neural HMMs
Paper
•
2211.13533
•
Published
OverFlow: Putting flows on top of neural transducers for better TTS
Paper
•
2211.06892
•
Published
Neural HMMs are all you need (for high-quality attention-free TTS)
Paper
•
2108.13320
•
Published
Matcha-TTS: A fast TTS architecture with conditional flow matching
Paper
•
2309.03199
•
Published
•
12
Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis
Paper
•
2306.09417
•
Published
•
3