@article{Shamei_Sullivan_Liu_Abdul-Mageed_Gick_2021, title={Automated detection of cannabis intoxication from speech}, volume={49}, url={https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3405}, abstractNote={<div class="page" title="Page 1"> <div class="layoutArea"> <div class="column"> <p>Machine learning can reliably distinguish a variety of mental and physical states based on acoustic alterations in the speech stream. Recent acoustic research found that cannabis intoxication results in significant differences in several acoustic correlates. Encouraged by these observations, we report models aimed at detecting cannabis intoxication from human speech. We exploit mel spectrograms from sober and intoxicated productions of sustained vowels, to train models under various gender-nuanced conditions (i.e., male-only, female-only, gender-agnostic) using convolutional neural networks (CNNs). In speaker-independent cross-validation, we report highly effective models (avg macro F 1 - females : 68.6%, males : 67.9%).</p> </div> </div> </div>}, number={2}, journal={Canadian Acoustics}, author={Shamei, Arian and Sullivan, Peter R. and Liu, Yadong and Abdul-Mageed, Muhammad and Gick, Bryan}, year={2021}, month={Jul.} }