Rafael Valle

Rafael Valle is a senior research scientist at NVIDIA focusing on generative models for audio. He received his interdisciplinary PhD in machine listening and improvisation from UC Berkeley where he was mainly advised by Prof. Sanjit Seshia and Prof. Edmund Campion.
Avatar photo

Posts by Rafael Valle

Conversational AI Sep 05, 2024

Achieving State-of-the-Art Zero-Shot Waveform Audio Generation across Audio Types

Stunning audio content is an essential component of virtual worlds. Audio generative AI plays a key role in creating this content, and NVIDIA is continuously... 6 MIN READ
Conversational AI Oct 03, 2020

Training Your Own Voice Font Using Flowtron

Recent conversational AI research has demonstrated automatically generating high quality, human-like audio from text. For example, you can use Tacotron 2 and... 12 MIN READ