The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS
Mar 21, 2026·,
,,,,,·
1 min read
K.-Y. Chen
Y.-C. Lin
Po-Chung (Bryan) Hsieh
H.-C. Chou
C.-F. Hsu
J.-L. Li
H. Lee
J.-J. Ding
This paper analyzes how multi-dimensional cues in natural-language instructions bind together to form gender bias in instruction-following text-to-speech (TTS) systems.
Accepted to INTERSPEECH 2026.

Authors
M.S. Student in Electrical and Computer Engineering
I am an M.S. student in Electrical and Computer Engineering at UC San Diego, with a B.S. in Electrical Engineering from National Taiwan University. I build AI agents and reinforcement learning methods for scientific discovery, including multi-agent systems for biomedical feature discovery and policy optimization for discrete generative models, and I previously worked as an LLM engineer intern at the Inventec Artificial Intelligence Center.