Automated detection of cannabis intoxication from speech
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%).
Downloads
Published
How to Cite
Issue
Section
License
Copyright on articles is held by the author(s). The corresponding author has the right to grant on behalf of all authors and does grant on behalf of all authors, a worldwide exclusive licence (or non-exclusive license for government employees) to the Publishers and its licensees in perpetuity, in all forms, formats and media (whether known now or created in the future)
i) to publish, reproduce, distribute, display and store the Contribution;
ii) to translate the Contribution into other languages, create adaptations, reprints, include within collections and create summaries, extracts and/or, abstracts of the Contribution;
iii) to exploit all subsidiary rights in the Contribution,
iv) to provide the inclusion of electronic links from the Contribution to third party material where-ever it may be located;
v) to licence any third party to do any or all of the above.
