A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
Preprint: arXiv:2310.05203 (Accepted to ASRU 2023)
This page provides audio samples of our singing voice conversion system (denoted as T13; the Nagoya University system) for The Singing Voice Conversion Challenge 2023.
Task 1: In-domain SVC
Target: IDM1
Sample: 30013
| Source | Target | T13 |
|---|---|---|
Sample: 30017
| Source | Target | T13 |
|---|---|---|
Sample: 30020
| Source | Target | T13 |
|---|---|---|
Sample: 30021
| Source | Target | T13 |
|---|---|---|
Sample: 30024
| Source | Target | T13 |
|---|---|---|
Target: IDF1
Sample: 30013
| Source | Target | T13 |
|---|---|---|
Sample: 30017
| Source | Target | T13 |
|---|---|---|
Sample: 30020
| Source | Target | T13 |
|---|---|---|
Sample: 30021
| Source | Target | T13 |
|---|---|---|
Sample: 30024
| Source | Target | T13 |
|---|---|---|
Task 2: Cross-domain SVC
Target: CDM1
Sample: 30013
| Source | Target | T13 |
|---|---|---|
Sample: 30017
| Source | Target | T13 |
|---|---|---|
Sample: 30020
| Source | Target | T13 |
|---|---|---|
Sample: 30021
| Source | Target | T13 |
|---|---|---|
Sample: 30024
| Source | Target | T13 |
|---|---|---|
Target: CDF1
Sample: 30013
| Source | Target | T13 |
|---|---|---|
Sample: 30017
| Source | Target | T13 |
|---|---|---|
Sample: 30020
| Source | Target | T13 |
|---|---|---|
Sample: 30021
| Source | Target | T13 |
|---|---|---|
Sample: 30024
| Source | Target | T13 |
|---|---|---|
Additional samples: https://anonymous7n.github.io/asru2023/
Ryuichi Yamamoto
Engineer/Researcher
I am a engineer/researcher passionate about speech synthesis. I love to write code and enjoy open-source collaboration on GitHub. Please feel free to reach out on Twitter and GitHub.