Entropy shows: is it real speech, or a clone?
DOI:
https://doi.org/10.36505/ExLing-2024/15/0003/000628Keywords:
Entropy, Cloned speech, Forensics, Formants, AIAbstract
This is an exploratory study that compares the conditional entropy formant values of naturally spoken words to the conditional entropy formant values of cloned vowels. It was hypothesized that cloned vowel formants, F1, F2, and F3, would have measurable and distinct differences compared to the formants of natural speech. This study shows that there are indeed variations in the entropy of Artificial Intelligence (AI) cloned vowels. These differences would be useful for forensic analyses and for distinguishing natural speech from AI generated imitations.
Downloads
References
Botinis, A., Goertz, G., Kontostavlaki, A., Anderson, T. 2023. Vowel discrimination of American English. ExLing 2023 Athens: Proceedings 14th International Conference of Experimental Linguistics, October 13-16. Athens, Greece.
The MathWorks Inc. 2023. MATLAB version: 9.13.0 (R2022b), Natick, Massachusetts: The MathWorks Inc. https://www.mathworks.com.
Goodfellow, I., Bengio, Y., Courville, A. 2016. Deep Learning. Cambridge, Massachusetts: The MIT Press.
Haglund, J.F. Jeppsson, H. Strömdahl. 2010. Different Senses of Entropy – Implications for Education. Entropy 12, 490-515. Doi: 10.3390/e12030490.
Peng, H. 2022. Mutual Information computation. (www.mathworks.com/matlabcentral/fileexchange/14888-mutual-information-computation).
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Terese Anderson, Grandon Goertz, Evan Ashworth (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
