SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Abstract
Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. Unlike most neural evaluation metrics that use hand-crafted features, SVSNet directly takes the raw waveform as input to more completely utilize speech information for prediction. SVSNet consists of encoder, co-attention, distance calculation, and prediction modules and is trained in an end-to-end manner. The experimental results on the Voice Conversion Challenge 2018 and 2020 (VCC2018 and VCC2020) datasets show that SVSNet outperforms well-known baseline systems in the assessment of speaker similarity at the utterance and system levels.
Keywords
Cite
@article{arxiv.2107.09392,
title = {SVSNet: An End-to-end Speaker Voice Similarity Assessment Model},
author = {Cheng-Hung Hu and Yu-Huai Peng and Junichi Yamagishi and Yu Tsao and Hsin-Min Wang},
journal= {arXiv preprint arXiv:2107.09392},
year = {2022}
}
Comments
To appear in IEEE Signal Processing Letters (SPL)