Automated detection of cannabis intoxication from speech

Authors

Abstract

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%).

Published

2021-07-07

How to Cite

1.
Shamei A, Sullivan PR, Liu Y, Abdul-Mageed M, Gick B. Automated detection of cannabis intoxication from speech. Canadian Acoustics [Internet]. 2021 Jul. 7 [cited 2021 Jul. 27];49(2). Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3405

Issue

Section

Article - Bio-Acoustics

Most read articles by the same author(s)

1 2 3 4 5 > >>