Speech & Language

Our research looks at ways to apply natural language processing (NLP), text-to-speech (TTS) synthesis, and other technologies to voice and animation needs in games.

Recent Publications

White "Animation" text and diamond logo on red to purple gradient background with abstract shapes.

GENEA Challenge 2023: Evaluating Gesture Generation with Two Speakers

This paper reports on the third GENEA Challenge, which benchmarks data-driven automatic co-speech gesture generation.

White "Animation" text and diamond logo on red to purple gradient background with abstract shapes.

GENEA Challenge 2022: Co-Speech Gesture Generation

This paper reports on the second GENEA Challenge, which benchmarks data-driven automatic co-speech gesture generation.

Seed Logo Content Creation with ML on a blue background

AIIDE22: Synthesis of Sound Effects Using Generative Models

Research paper from AIIDE22: Generating controllable variations of sound effects that can be used in the creative process of sound designers.

Latest News

White "Animation" text and diamond logo on red to purple gradient background with abstract shapes.

SEED’s Voice2Face Honored by Fast Company

Electronic Arts and SEED’s Voice2Face project have been named one of Fast Company’s Next Big Things in Tech!