Gender Bias in Instruction-Guided Speech Synthesis Models
Journal
2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Proceedings of the Conference Findings, NAACL 2025
Start Page
5387
End Page
5413
ISBN (of the container)
979-889176195-7
Date Issued
2025-04-29
Author(s)
Kuan, Chun-Yi
Abstract
Recent advancements in controllable expressive speech synthesis, especially in text-to-speech (TTS) models, have allowed for the generation of speech with specific styles guided by textual descriptions, known as style prompts. While this development enhances the flexibility and naturalness of synthesized speech, there remains a significant gap in understanding how these models handle vague or abstract style prompts. This study investigates the potential gender bias in how models interpret occupation-related prompts, specifically examining their responses to instructions like “Act like a nurse”. We explore whether these models exhibit tendencies to amplify gender stereotypes when interpreting such prompts. Our experimental results reveal the model’s tendency to exhibit gender bias for certain occupations. Moreover, models of different sizes show varying degrees of this bias across these occupations.
Event(s)
2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, NAACL 2025
Publisher
Association for Computational Linguistics
Type
conference paper