Article
Version 1
Preserved in Portico This version is not peer-reviewed
Voice-Cloning Artificial-Intelligence Speakers Can Also Mimic Human-Specific Vocal Expression
Version 1
: Received: 8 December 2023 / Approved: 12 December 2023 / Online: 13 December 2023 (04:14:46 CET)
How to cite: Chen, W.; Jiang, X. Voice-Cloning Artificial-Intelligence Speakers Can Also Mimic Human-Specific Vocal Expression. Preprints 2023, 2023120807. https://doi.org/10.20944/preprints202312.0807.v1 Chen, W.; Jiang, X. Voice-Cloning Artificial-Intelligence Speakers Can Also Mimic Human-Specific Vocal Expression. Preprints 2023, 2023120807. https://doi.org/10.20944/preprints202312.0807.v1
Abstract
This study investigated the capability of vocal-identity-cloning Artificial Intelligence (AI) to encode human-specific confident, doubtful, and neutral-intending emotive states. Linear mixed-effects models and machine learning classification with eXtreme Gradient Boosting were employed to examine the underlying acoustic signatures from 2,700 audio clips, comprising of sentences spoken by human speakers and two sets of equivalences (AI-Geography/AI-Trivia, based on the trained text) generated by voice-cloning models designed to clone human speakers’ identities. Compared with neutral-intending voice, human speakers lengthened their vocal tract, raised the fundamental frequency, and increased Chroma constant-Q transform when they intended to be confident; An opposite pattern was shown when they intended to be doubtful. The two sets of AI sounds displayed a similar pattern to human speech, suggesting a shared mechanism for encoding vocal expression across sources. The 1,000 times training-testing classification models reported an in-group advantage for AI sources. The algorithms, trained on AI-Geography/AI-Trivia, resulted in higher accuracies when tested within these AI sources than when tested on human audio. All between-source classifications reported above-chance-level (1/3) accuracies. These findings highlighted that voice-cloning AI, the widely used conversational agent, can learn and generate human-specific vocally-expressed confidence.
Keywords
Voice cloning; Affective computing; Vocal confidence; Social AI; Human-computer interaction
Subject
Social Sciences, Cognitive Science
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment