# Acoustic and perceptual differences between standard and accented speech and their voice clones

arXiv: https://arxiv.org/abs/2604.01562 · HTML: https://mlsanity.com/paper/2604.01562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 59 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2008.03648/) (2020)
- [AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines](https://mlsanity.com/paper/2010.11567/) (2020)
- [Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion](https://mlsanity.com/paper/2008.12527/) (2020)
- [The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods](https://mlsanity.com/paper/1804.04262/) (2018)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Warning: Humans Cannot Reliably Detect Speech Deepfakes](https://mlsanity.com/paper/2301.07829/) (2023)
- ["It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services](https://mlsanity.com/paper/2504.09346/) (2025)
- [Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model](https://mlsanity.com/paper/2405.09768/) (2024)
- [Forensic deepfake audio detection using segmental speech features](https://mlsanity.com/paper/2505.13847/) (2025)
- [Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection](https://mlsanity.com/paper/2601.23066/) (2026)
- [Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion](https://mlsanity.com/paper/2309.02133/) (2023)
- [Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching](https://mlsanity.com/paper/2503.18032/) (2025)
- [Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation](https://mlsanity.com/paper/2603.21078/) (2026)
- [Automatic Evaluation of Speaker Similarity](https://mlsanity.com/paper/2207.00344/) (2022)
- [SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models](https://mlsanity.com/paper/2406.08445/) (2024)

## Abstract (arXiv)

Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We compare standard and heavily accented Mandarin speech and their voice clones using a combined computational and perceptual design. Embedding-based analyses showed larger original-clone distances for accented speakers in several speaker-discriminative embedding spaces, but this difference disappeared after adjusting for each speaker's within-original baseline variability. In the perception study, clones are rated as more similar to their originals for standard than for accented speakers, and intelligibility increases from original to clone, with a larger gain for accented speech. These results show that accent variation can shape perceived identity match and intelligibility in voice cloning even when it is not observed in baseline-adjusted speaker-embedding distance, and they motivate treating accent preservation as an explicit component of speaker identity preservation, rather than assuming that it is fully captured by off-the-shelf speaker-discriminative embeddings.