Abstract
This study considers an approach to the analysis of human speech using neural networks to perform the task of determining the state of alcahol intoxication. In the course of the study, a personal data set was created, consisting of 340 audio files, and increased to the size of 1020 audio files, using augmentation methods, namely slowing down and speeding up audio files. As input data for neural networks, spectrograms and MFCC visualization with size of 256 × 256 and 512 × 512 pixels were considered, thanks to which four VGG16 models were trained. As a result of the study, the best model was identified, namely, trained on spectrograms of size 512 × 512, having F-score and UAR values of 0.73 and 0.77 for the test samples, and 0.82 and 0.83 in the form of averages of 10-fold cross-validation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andrews, M.L., Cox, W.M., Smith, R.G.: Effects of alcohol on the speech of non alcoholics. Central States Speech J. 28(2), 140-143 (1977). https://doi.org/10.1080/10510977709367933
Beam, S.L., Gant, R.W., Mecham, M.J.: Communication deviations in alcoholics; a pilot study. J. Stud. Alcohol 39(3), 548–551 (1978)
Sobell, L.C., Sobell, M.B.: Effects of alcohol on the speech of alcoholics. J. Speech Hear. Res. 15(4), 861–868 (1972)
Chin, S., Pisoni, D.: Alcohol and Speech. Brill (1997)
World Helth Organization: Alcohol. https://www.who.int/news-room/fact-sheets/detail/alcohol. Accessed 20 June 2023
Brenner, M., Cash, J.R.: Speech analysis as an index of alcohol intoxication–the Exxon Valdez accident. Aviat. Space Environ. Med. 62(9 Pt 1), 893–898 (1991)
Klingholz, F., Penning, R., Liebhardt, E.: Recognition of low-level alcohol intoxication from speech signal. J. Acoustical Society of America 84(3), 929–935 (1988)
Zissman, M.A.: Comparison of four approaches to automatic language identification of telephone speech. IEEE Trans. Speech and Audio Processing 4(1), 31 (1996)
Pisoni, D.B., Martin, C.S.: Effects of alcohol on the acoustic‐phonetic properties of speech: perceptual and acoustic analyses. Alcoholism: Clinical and Experimental Res. 13(4), 577–587 (1989)
Sigmund, M., Zelinka, P.: Analysis of voiced speech excitation due to alcohol intoxication. Information Technology and Control 40(2), 143–150 (2011)
Johnson, K., Pisoni, D.B., Bernacki, R.H.: Do voice recordings reveal whether a person is intoxicated? A Case Study. Phonetica 47(3–4), 215–237 (1990)
Crow, K.E., Batt, R.D.: Human Metabolism of Alcohol (1989)
Lester, L., Skousen, R.: The Phonology of Drunkenness. Papers from the parasession on natural phonology, pp. 233–239 (1974)
Biadsy, F., Wang, W.Y., Rosenberg, A., Hirschberg, J.B.: Intoxication detection using phonetic, phonotactic and prosodic cues. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 3209–3212 (2011). https://doi.org/10.21437/Interspeech.2011-803
Bojanić, M., Delić, V., Karpov, A.: Call redistribution for a call center based on speech emotion recognition. Appl. Sci. 10(13), 4653 (2020)
Lincoln, N.B., Mulley, G.P., Jones, A.C., McGuirk, E., Lendrem, W., Mitchell, J.R.A.: Effectiveness of speech therapy for aphasic stroke patients: a randomised controlled trial. The Lancet 323(8388), 1197–1200 (1984)
Leanderson, R., Meyerson, B.A., Persson, A.: Effect of L-dopa on speech in Parkinsonism: an EMG study of labial articulatory function. J. Neurol. Neurosurg. Psychiatry 34(6), 679–681 (1971)
Watson, P.E., Watson, I.D., Batt, R.D.: Prediction of blood alcohol concentrations in human subjects. updating the widmark equation. Journal of Studies on Alcohol 42(7), 547–556 (1981)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv, arXiv:1409.1556 (2014)
Ferguson, M., Ak, R., Lee, Y.T.T., Law, K.H.: Automatic localization of casting defects with convolutional neural networks. In: 2017 IEEE International Conference on Big Data, Boston, MA, USA, pp. 1726–1735 (2017)
Bonela, A.A., He, Z., Nibali, A., Norman, T., Miller, P.G., Kuntsche, E.: Audio-based deep learning algorithm to identify alcohol inebriation (ADLAIA). Alcohol 109, 49–54 (2023)
Rustore: Gradus. https://apps.rustore.ru/app/ru.gradus.app. Accessed 13 Sep 2023
Google Play: Gradus. https://play.google.com/store/apps/details?id=ru.gradus.app. Accessed 13 Sep 2023
Irkutsk Supercomputer Center SB RAS. http://hpc.icc.ru/. Accessed 12 July 2023
Acknowledgments
This research was funded by the Ministry of Science and Higher Education of the Russian Federation within the framework of scientific projects carried out by teams of research laboratories of educational institutions of higher education subordinate to the Ministry of Science and Higher Education of the Russian Federation, project number FEWM-2020–0042. The authors would like to thank the Irkutsk Supercomputer Center of SB RAS for providing access to the HPC-cluster «Akademik V.M. Matrosov» [24].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Laptev, P., Litovkin, S., Kostyuchenko, E. (2023). Determining Alcohol Intoxication Based on Speech and Neural Networks. In: Karpov, A., Samudravijaya, K., Deepak, K.T., Hegde, R.M., Agrawal, S.S., Prasanna, S.R.M. (eds) Speech and Computer. SPECOM 2023. Lecture Notes in Computer Science(), vol 14338. Springer, Cham. https://doi.org/10.1007/978-3-031-48309-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-48309-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48308-0
Online ISBN: 978-3-031-48309-7
eBook Packages: Computer ScienceComputer Science (R0)