← Search

Rudrabha Mukhopadhyay

2 accepted papers

2024

Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data

AAAI 2024technical

This work tackles the important task of understanding out-of-distribution behavior in two prominent types of generative models, i.e., GANs and Diffusion models. Understanding this behavior is crucial in understanding their broader utility and risks as these systems are increasingly deployed in our d…

2020

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis

CVPR 2020poster

Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural speech given only the lip movements of a speaker. Acknowledging t…

Cited by 130PDFcodeScholar