arXiv AI
Voice "Cloning" is Style Transfer
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
Acoustic and perceptual differences between standard and accented speech and their voice clones
arXiv:2604. 01562v2 Announce Type: replace-cross Abstract: Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences.
arXiv Computation and Language
Aug 28
Your Voice Cloning System is Secretly a Voice Anonymizer
The paper demonstrates that the multilingual voice cloning model XTTSv2 can be repurposed for speaker anonymization without retraining. By conditioning on a pseudo-speaker and using an iterative refinement strategy, the authors balance privacy and intelligibility, achieving near‑optimal privacy (EER ≈ 0.49) and competitive speech quality across seven European languages. The method outperforms dedicated anonymization baselines and requires no language‑specific training.
arXiv AI
Oct 15
Known-Voice Cloning and the Limits of Personality Transfer for Character Design
arXiv:2610.18669v1 Announce Type: cross Abstract: Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitra...
arXiv Computation and Language
Aug 21
Does Listening Matter? Backchanneling and Nodding in AI Clone
arXiv:2608. 19527v1 Announce Type: cross Abstract: AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen.
arXiv Computation and Language
Aug 24
The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints
The article critiques the notion that a person's voice is a stable, unique biometric trace—termed a voiceprint—by reviewing historical, forensic, and technological evidence. It argues that voices are highly dynamic and context-dependent, and that the voiceprint metaphor misrepresents probabilistic speaker information as a fixed identity marker. The authors emphasize that speaker recognition should account for within-speaker variability, domain mismatch, and synthetic manipulation rather than rely on an assumed stable voiceprint.
arXiv AI
Sep 30
HEAR: Real Voices, Real Bias: A Large-Scale Human-Recorded, Demographically Diverse Benchmark for Audio Language Models
arXiv:2609.35952v1 Announce Type: cross Abstract: We introduce HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising 87k real hum...