Article

Finding the Human Voice in AI: Insights on the Perception of AI-Voice Clones from Naturalness and Similarity Ratings

2025-06-03

Abstract excerpt

<p>AI-generated voice clones are important tools in language learning, audiobooks, and assistive technology, but often struggle to replicate key prosodic features such as dynamic F0 variation. The impact of these differences on speech perception remain underexplored. To address this, we conducted two behavioural tasks, evaluating listeners’ ratings of naturalness and similarity for human speech, three AI voice clo...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 1ebd6a8c-8b5f-5a53-856e-d05677bddd53
DOI: 10.31234/osf.io/y6e35_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Finding the Human Voice in AI: Insights on the Perception of AI-Voice Clones from Naturalness and Similarity RatingsDOI 10.31234/osf.io/y6e35_v1Read

Prosodic cues strengthen human-AI voice boundaries: Listeners do not easily perceive human speakers and AI clones as the same personSemantic proximity Read

Does Speech Prosody Shape Social Perception Equally for AI and Human Voices? A 16-Dimension Rating StudySemantic proximity Read

Voice-Cloning Artificial-Intelligence Speakers Can Also Mimic Human-Specific Vocal ExpressionSemantic proximity Read

Human brains implicitly and rapidly distinguish AI from human voices before decoding prosodic meaningSemantic proximity Read

Perception and Social Evaluation of Cloned and Recorded Voices: Effects of Familiarity and Self-Relevance.Semantic proximity Read

Perception of Humanness Is Affected by Speech ContentSemantic proximity Read

Voice clones sound realistic but not (yet) hyperrealisticSemantic proximity Read

Voice clones sound realistic but not (yet) hyperrealisticSemantic proximity Read

AImoclips: Benchmarking Emotion Conveyance in Text-to-Music Generation Using a Dimensional Valence-Arousal FrameworkSemantic proximity Read

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language ModelsSemantic proximity Read

Calibrating Gemini to Human Raters in Spoken Language Assessment for EFL Learners in AsiaSemantic proximity Read

Perception of concatenative vs. neural text-to-speech (TTS): Differences in intelligibility in noise and language attitudesSemantic proximity Read