Related Experiment Video
Updated: Aug 10, 2025
05:48
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
1.6K
ArtiLock: Smartphone User Identification Based on Physiological and Behavioral Features of Monosyllable Articulation
Aslan B Wong1, Ziqi Huang1, Xia Chen2
1College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518061, China.
Sensors (Basel, Switzerland)
|February 11, 2023
Summary
This study introduces a novel smartphone authentication system analyzing vocal tract physiology and behavior. It achieves 99% accuracy with a single utterance, outperforming traditional voice biometrics.
Area of Science:
- Biometrics
- Human-Computer Interaction
- Signal Processing
Background:
- Traditional voiceprint authentication faces challenges with environmental noise and large sample requirements.
- Existing behavioral biometrics struggle with accuracy and adaptability to varying conditions.
Purpose of the Study:
- To develop a robust smartphone user authentication system leveraging physiological and behavioral vocal characteristics.
- To enhance security and user-friendliness by utilizing single utterances for identity verification.
Main Methods:
- Simultaneous transmission and reception of speech and ultrasonic signals using smartphone hardware.
- Analysis of vocal tract articulation, tongue position, and lip movement for feature extraction.
- Development of an algorithm to distinguish legitimate users from attackers based on unique vocal patterns.
Main Results:
- Achieved an average accuracy of 99% for user authentication.
- Demonstrated a low equal error rate of 0.5% across diverse environmental conditions.
- Validated the system's effectiveness with single utterances, reducing sample size requirements.
Conclusions:
- The proposed physiological and behavioral authentication method offers superior accuracy and environmental adaptability compared to conventional voice biometrics.
- The system provides a user-friendly and highly secure solution against mimicry attacks.
- This approach represents a significant advancement in secure and efficient smartphone user authentication.
