VoxSim: A perceptual voice similarity dataset
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929438110777344 |
|---|---|
| author | Ahn, Junseok Kim, Youkyum Choi, Yeunju Kwak, Doyeop Kim, Ji-Hoon Mun, Seongkyu Chung, Joon Son |
| author_facet | Ahn, Junseok Kim, Youkyum Choi, Yeunju Kwak, Doyeop Kim, Ji-Hoon Mun, Seongkyu Chung, Joon Son |
| contents | This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and benchmarking of speaker similarity prediction models. We provide baseline results of speaker similarity prediction models on the VoxSim test set and further demonstrate that the model trained on our dataset generalises to the out-of-domain VCC2018 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18505 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VoxSim: A perceptual voice similarity dataset Ahn, Junseok Kim, Youkyum Choi, Yeunju Kwak, Doyeop Kim, Ji-Hoon Mun, Seongkyu Chung, Joon Son Audio and Speech Processing This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and benchmarking of speaker similarity prediction models. We provide baseline results of speaker similarity prediction models on the VoxSim test set and further demonstrate that the model trained on our dataset generalises to the out-of-domain VCC2018 dataset. |
| title | VoxSim: A perceptual voice similarity dataset |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.18505 |