Acoustic and perceptual differences between standard and accented speech and their voice clones
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918534212222976 |
|---|---|
| author | Yang, Tianle Sun, Chengzhe Rose, Phil Lyu, Siwei |
| author_facet | Yang, Tianle Sun, Chengzhe Rose, Phil Lyu, Siwei |
| contents | 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 normalizing against 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 reflected in baseline-normalized 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01562 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Acoustic and perceptual differences between standard and accented speech and their voice clones Yang, Tianle Sun, Chengzhe Rose, Phil Lyu, Siwei Sound Artificial Intelligence Computation and Language Computers and Society Human-Computer Interaction 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 normalizing against 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 reflected in baseline-normalized 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. |
| title | Acoustic and perceptual differences between standard and accented speech and their voice clones |
| topic | Sound Artificial Intelligence Computation and Language Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.01562 |