amphion/Diff-SSL-G-Comp
Updated
•
29
•
1
AI & ML interests
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Recent Activity
amphion's activity
Emilia-YODAS
1
5
#12 opened about 2 months ago
by
mrfakename
Setsugesuka
updated
a
dataset
5 days ago
Hecheng0625
updated
a
model
5 days ago
RMSnow
updated
3
models
5 days ago
wli3221134
updated
a
dataset
9 days ago
wli3221134
published
a
dataset
9 days ago
lmxue
authored
a
paper
about 1 month ago
lmxue
authored
a
paper
about 2 months ago
Hecheng0625
authored
a
paper
3 months ago
jiaqili3
authored
a
paper
3 months ago
HarryHe
authored
3
papers
3 months ago
Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
Paper
•
2501.15907
•
Published
•
16
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
Paper
•
2407.05361
•
Published
•
2
SpMis: An Investigation of Synthetic Spoken Misinformation Detection
Paper
•
2409.11308
•
Published
drwuz
authored
5
papers
10 months ago
Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder
Paper
•
2311.14957
•
Published
•
2
AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models
Paper
•
2304.00830
•
Published
•
2
Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion
Paper
•
2310.11160
•
Published
CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing
Paper
•
2401.12264
•
Published
SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion
Paper
•
2402.12660
•
Published