VoxSim: A perceptual voice similarity dataset

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 e...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Ahn, Junseok, Kim, Youkyum, Choi, Yeunju, Kwak, Doyeop, Ji-Hoon, Kim, Mun, Seongkyu, Joon Son Chung
Format: Article
Language:English
Subjects:
Datasets
Prediction models
Predictions
Similarity
Speech recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422