The researchers have discovered that the sound of a person’s voice can reveal whether they are sleep-deprived or well-rested. This breakthrough has led to the development of an artificial intelligence program that can accurately identify individuals who are lacking sufficient sleep.
A recent report from France’s National Centre for Scientific Research (CNRS) revealed that three out of every ten people in France do not get enough sleep, receiving less than six hours of sleep per night. This statistic has tripled over the past decade, with various factors such as screen time contributing to the problem. Lack of sleep can result in chronic fatigue, mood disorders, and an increased risk of accidents.
A study published in PLoS Computational Biology by the Vigilance, Fatigue, Sleep and Public Health (VIFASOM) research team in Paris, in collaboration with CNRS researchers, highlights the ability to identify sleep deprivation by analyzing voice recordings using artificial intelligence technology.
During the study, 22 women aged 30 to 50 were subjected to only three hours of sleep per night for two consecutive nights to observe changes in their voices. The researchers found two key effects of sleep deprivation on vocal characteristics – alterations in prosody (speech melody, voice changes, speech rate variation) and timbre (clear vs. hoarse voice).
The team then trained the AI system to differentiate between the voice recordings and accurately identify signs of sleep deprivation. By employing machine learning, the program can now successfully detect differences in voices and recognize sleep-deprived individuals. This development opens up possibilities for utilizing AI-driven methods to detect sleep deprivation through voice analysis, particularly in industries where alertness is crucial.
The researchers are looking forward to expanding this methodology to create additional vocal markers that can indicate attention deficits or a person’s overall physiological state. This advancement could have significant implications in various professional fields, offering a more efficient way to monitor and address sleep-related issues.
