New model tracks vocal fold fatigue as it develops, study shows

A new modeling technique for vocal fold fatigue, as reported in the International Journal of Information and Communication Technology, could revolutionize the detection and monitoring of voice-related issues. The article, authored by Xi Zhang et al., introduces a physics-based framework known as physics-informed joint simulation and identification (PJSF). This innovative approach treats vocal fold fatigue as a continuously evolving process rather than a static condition.

Vocal folds, also known as vocal cords, are essential for speech, singing, and various vocalizations. Vocal fold fatigue, characterized by diminished vocal efficiency, poorer voice quality, and increased effort during speaking, can affect anyone but is particularly common among individuals who exert their voices more than average, such as public speakers, teachers, call center operators, and singers.

The PJSF model integrates equations that describe the system's changes over time with acoustic recordings and laryngovibrography, which measure vocal fold vibrations. This combination enables the system to accurately identify fatigue while minimizing false alarms. In a study involving 20 volunteers, the PJSF model demonstrated its effectiveness by correctly detecting fatigue while avoiding false alarms.

The implications of this research are significant. With further development, the PJSF model could become a powerful tool for monitoring vocal strain and providing personalized guidance on voice use. This could be particularly beneficial for individuals in professions that require constant voice use, helping to prevent vocal fold fatigue and related issues.