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
Shiqi Han — most-cited papers & profile · Speech Audio
← authors
·
overview
Shiqi Han
1
papers ·
0
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models
2026
Top co-authors
Beena Ahmed
· 1
Haoyang Zhang
· 1
Hexin Liu
· 1
Julien Epps
· 1
Qiquan Zhang
· 1
Xiangyu Zhang
· 1
Yuxin Li
· 1
Topics
Audio Generation
Speech Recognition
Text-to-Speech