Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Nov;84(6):808-813.
doi: 10.15288/jsad.22-00375. Epub 2023 Jun 9.

Detection of Alcohol Intoxication Using Voice Features: A Controlled Laboratory Study

Brian Suffoletto  1 , Ayman Anwar  2 , Sean Glaister  1 , Ervin Sejdic  2   3
Affiliations

Detection of Alcohol Intoxication Using Voice Features: A Controlled Laboratory Study

Brian Suffoletto et al. J Stud Alcohol Drugs. 2023 Nov.

Abstract

Objective: Devices such as mobile phones and smart speakers could be useful to remotely identify voice alterations associated with alcohol intoxication that could be used to deliver just-in-time interventions, but data to support such approaches for the English language are lacking. In this controlled laboratory study, we compare how well English spectrographic voice features identify alcohol intoxication.

Method: A total of 18 participants (72% male, ages 21-62 years) read a randomly assigned tongue twister before drinking and each hour for up to 7 hours after drinking a weight-based dose of alcohol. Vocal segments were cleaned and split into 1-second windows. We built support vector machine models for detecting alcohol intoxication, defined as breath alcohol concentration > .08%, comparing the baseline voice spectrographic signature to each subsequent timepoint and examined accuracy with 95% confidence intervals (CIs).

Results: Alcohol intoxication was predicted with an accuracy of 98% (95% CI [97.1, 98.6]); mean sensitivity = .98; specificity = .97; positive predictive value = .97; and negative predictive value = .98.

Conclusions: In this small, controlled laboratory study, voice spectrographic signatures collected from brief recorded English segments were useful in identifying alcohol intoxication. Larger studies using varied voice samples are needed to validate and expand models.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
The classification scheme of the proposed algorithms. First, the voice records are separated into foreground and background vocals to remove noise and vocals in the background. Second, a sliding window of 1 second length slides over the voice foreground to extract the spectrogram features for different breath alcohol concentration (BrAC) levels. Then, the extracted features are fed into the corresponding support vector machine (SVM) model to separate the baseline (BL) level from the intoxicated vocals. Finally, the separated SVM predictions are fed to an ensemble classifier that predicts the presence of intoxication in the voice using a majority voting produced by the SVM classifiers.
See this image and copyright information in PMC

References

    1. Agurto C., Cecchi G. A., Norel R., Ostrand R., Kirkpatrick M., Baggott M. J., Wardle M. C., de Wit H., Bedi G. Detection of acute 3,4-methylenedioxymethamphetamine (MDMA) effects across protocols using automated natural language processing. Neuropsychopharmacology. 2020;45:823–832. doi: 10.1038/s41386-020-0620-4. - DOI - PMC - PubMed
    1. Alpert H. R., Slater M. E., Yoon Y.-H., Chen C. M., Winstanley N., Esser M. B. Alcohol consumption and 15 causes of fatal injuries: A systematic review and meta-analysis. American Journal of Preventive Medicine. 2022;63(2):286–300. doi: 10.1016/j.amepre.2022.03.025. - DOI - PMC - PubMed
    1. Andrianopoulos A. V., Darrow K. N., Chen J. Multimodal standardization of voice among four multicultural populations: Fundamental frequency and spectral characteristics. Journal of Voice: Official Journal of the Voice Foundation. 2001;15(2):194–219. doi: 10.1016/S0892-1997(01)00021-2. - DOI - PubMed
    1. Bae S., Chung T., Ferreira D., Dey A. K., Suffoletto B. Mobile phone sensors and supervised machine learning to identify alcohol use events in young adults: Implications for just-in-time adaptive interventions. Addictive Behaviors. 2018;83:42–47. doi: 10.1016/j.addbeh.2017.11.039. - DOI - PMC - PubMed
    1. Baumeister B., Schiel F. INTERSPEECH. Lyons, France: 2013. Aug, 2013. Human perception of alcoholic intoxication in speech.https://www.isca-speech.org/archive/pdfs/interspeech_2013/baumeister13_i...

Publication types

LinkOut - more resources