Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 22, 2026Interacting with Computers

Beyond accuracy: user perception of differential privacy in speech emotion recognition

View Full Paper
Ask AI
Bookmark
Share

Authors

LFLe FangJLJiajuan LiCFCong Fang

Discussion

Loading...

Member takes

Overview

Randomized trial investigates user perceptions of privacy in speech emotion recognition, suggesting enhanced trust through transparency.

Key Points

  • This study aims to explore how user perceptions of privacy affect trust and acceptance in speech emotion recognition systems.
  • Formative study with 16 users to understand privacy concerns and expectations.
  • Designed a two-stage differentially private SER framework integrated into an online platform.
  • A/B study with 32 users to assess the impact of privacy configurations on perceived usefulness and trust.
  • Transparent privacy mediation significantly enhances user trust and perceived security, p<0.05.
  • User-configurable privacy settings show higher acceptance rates compared to non-configurable options, p<0.01.
  • Recognition performance remained stable despite the implementation of privacy measures.

Cite This Study

Fang et al. (2026) studied this question.

synapsesocial.com/papers/6a605dfa4163e025518d7d01https://doi.org/10.1093/iwc/iwag035
View Full Paper
Ask AI
Bookmark
Share