Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observations using human observers increases the costs of conducting research and monitoring interventions in practice. To address this issue, we conducted a proof of concept examining whether artificial intelligence could measure vocal stereotypy in individuals with autism. More specifically, we used an artificial neural network with over 1,500 minutes of audio data from eight different individuals to train and test models to measure vocal stereotypy. Our results showed that our artificial neural network performed adequately (i.e., session-by-session correlation near or above .80 with a human observer) in measuring engagement in vocal stereotypy for six of eight participants. That said, researchers need to conduct additional research to further improve the generalizability of the approach.
Artificial intelligence for the measurement of vocal stereotypy
