Awesome Speech Audio
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Yakun Song — most-cited papers & profile · Speech Audio
← authors
·
overview
Yakun Song
3
papers ·
0
citations ·
16
h-index
Fudan University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
2025
MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation
2025
Language Model Can Listen While Speaking
2024
Top co-authors
Chenpeng Du
· 3
Yuping Wang
· 3
Jiawei Chen
· 2
Ziyang Ma
· 2
Dongya Jia
· 1
Dongya Jia
· 1
Guanrou Yang
· 1
Jian Cong
· 1
Jian Cong
· 1
Jian Wu
· 1
Xiaobin Zhuang
· 1
Xiaobin Zhuang
· 1
Topics
Speech Recognition
Text-to-Speech
Audio Generation
Speech Translation
Music Generation
Audio Understanding
Multimodal Audio