Sreevatsank Kadaveru

Sreevatsank Kadaveru

Ph.D. Student, ECE, UC San Diego

Audio-StyleCLIP

ECE 285: Deep Generative Models with Preyaa Patel and Varun Pawar
Audio-StyleCLIP architecture: an image encoder and latent mapper edit a StyleGAN latent under a loss computed against a spoken prompt

Extended StyleCLIP with AudioCLIP, adapted for spoken prompts, to perform style transfer onto an image using an audio styling input.

Report

All research