HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS
Paper
•
2309.13907
•
Published
YuanjunLv
Bakerbunker
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for
Expressive Long-form TTS
authored
a paper
about 1 month ago
Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with
Progressive Constraints in a Dual-mode Training Strategy
authored
a paper
about 1 month ago
Single-Codec: Single-Codebook Speech Codec towards High-Performance
Speech Generation
Organizations
authored
4
papers
about 1 month ago
Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy
Paper
•
2406.09844
•
Published
Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation
Paper
•
2406.07422
•
Published
•
1
Qwen3-Omni Technical Report
Paper
•
2509.17765
•
Published
•
135
authored
5
papers
over 1 year ago
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Paper
•
2402.07729
•
Published
Qwen2-Audio Technical Report
Paper
•
2407.10759
•
Published
•
62
Vec-Tok Speech: speech vectorization and tokenization for neural speech generation
Paper
•
2310.07246
•
Published
•
1
FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter
Paper
•
2406.08196
•
Published
SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation
Paper
•
2310.05051
•
Published