GTC 2020: The SpeechBrain Project
After clicking “Watch Now” you will be prompted to login or join.
Click “Watch Now” to login or join the NVIDIA Developer Program.
The SpeechBrain Project
Mirco Ravanelli, Mila - Université de Motréal
SpeechBrain is an open-source project that aims to develop an all-in-one speech toolkit based on PyTorch. Our goal is to create a single, flexible, user-friendly toolkit that can be used to easily develop state-of-the-art speech technologies. SpeechBrain will be a standalone framework that can significantly speed up research and development of speech and audio processing techniques. Indeed, it's a lot easier to familiarize oneself with a single toolkit than to learn several different frameworks, as one must do today. Moreover, using a single platform makes it easier to build a strong and fruitful community where members can share models, codes, baselines, and suggestions with a possible positive impact in the field of speech technologies. SpeechBrain is currently under development, and a first alpha version will be available in the next months. We'll describe the motivations, goals, and current status of the project.