You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.

close
    
Session Name: Machine Learning Summit: Developing and Running Neural Audio in Constrained Environments
Speaker(s): Carter Huffman, Brendan Kelly
Company Name(s): Modulate.ai, Modulate.ai
Track / Format: Machine Learning Summit
Overview: Speech recognition, manipulation, and synthesis are opening up new types of experiences in games; but the deep neural networks that achieve state-of-the-art performance at these tasks are difficult to develop and use efficiently.The first part of this talk explores challenges and solutions for developing neural speech systems that meet gaming-centric requirements, and do so through the lens of an early-stage startup. Strategies for effective iteration with small team sizes are discussed, along with efficient use of limited compute resources.The second part of the talk covers methods for running audio neural networks on a device, specifically focusing on real-time audio manipulation and synthesis. Included are lessons-learned about aspects of audio neural networks for both traditional audio practitioners (e.g. choice of sample rates, buffer sizes, memory allocations) and traditional machine learning practitioners (e.g. suitability of deployment frameworks, model distillation).

GDC 2020

Carter Huffman

Modulate.ai

Brendan Kelly

Modulate.ai

free content

Machine Learning Summit

Programming