Quantifying Source Speaker Leakage in One-to-One Voice Conversion
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916702147575808 |
|---|---|
| author | Wellington, Scott Liu, Xuechen Yamagishi, Junichi |
| author_facet | Wellington, Scott Liu, Xuechen Yamagishi, Junichi |
| contents | Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a HiFi-GAN vocoder, we compare information leakage for a range speaker characteristics; assuming a "worst-case" white-box scenario, we quantify our confidence to perform inference and narrow the pool of likely source speakers, reinforcing the regulatory obligation and moral duty that providers of synthetic voices have to ensure the privacy of their speakers' data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantifying Source Speaker Leakage in One-to-One Voice Conversion Wellington, Scott Liu, Xuechen Yamagishi, Junichi Sound Cryptography and Security Audio and Speech Processing Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a HiFi-GAN vocoder, we compare information leakage for a range speaker characteristics; assuming a "worst-case" white-box scenario, we quantify our confidence to perform inference and narrow the pool of likely source speakers, reinforcing the regulatory obligation and moral duty that providers of synthetic voices have to ensure the privacy of their speakers' data. |
| title | Quantifying Source Speaker Leakage in One-to-One Voice Conversion |
| topic | Sound Cryptography and Security Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.15822 |