Mandarin Electrolaryngeal Speech Voice Conversion using Cross-domain Features
Abstract
Patients who have had their entire larynx removed, including the vocal folds, owing to throat cancer may experience difficulties in speaking. In such cases, electrolarynx devices are often prescribed to produce speech, which is commonly referred to as electrolaryngeal speech (EL speech). However, the quality and intelligibility of EL speech are poor. To address this problem, EL voice conversion (ELVC) is a method used to improve the intelligibility and quality of EL speech. In this paper, we propose a novel ELVC system that incorporates cross-domain features, specifically spectral features and self-supervised learning (SSL) embeddings. The experimental results show that applying cross-domain features can notably improve the conversion performance for the ELVC task compared with utilizing only traditional spectral features.
Keywords
Cite
@article{arxiv.2306.06653,
title = {Mandarin Electrolaryngeal Speech Voice Conversion using Cross-domain Features},
author = {Hsin-Hao Chen and Yung-Lun Chien and Ming-Chi Yen and Shu-Wei Tsai and Yu Tsao and Tai-shih Chi and Hsin-Min Wang},
journal= {arXiv preprint arXiv:2306.06653},
year = {2023}
}
Comments
Accepted to INTERSPEECH 2023