Scholar
Shansong Liu
Google Scholar ID: ndVYtaUAAAAJ
TeleAI
Music AI
TTS
LLM
Multi-modal LLM
Audio codec
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,056
H-index
18
i10-index
26
Publications
20
Co-authors
0
Publications
7 items
Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework
2026
Cited
0
Unified Audio Generation and Editing via Joint Condition Modeling and Progressive Training
2026
Cited
0
Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
2026
Cited
0
High-Fidelity Generative Audio Compression at 0.275kbps
2026
Cited
0
Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
2025
Cited
0
YuE: Scaling Open Foundation Models for Long-Form Music Generation
2025
Cited
0
Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer
arXiv.org · 2024
Cited
0
