AgoraResearch hub
ExploreLibraryProfile
Account
Florian Metze
Scholar

Florian Metze

Google Scholar ID: FsEP7AgAAAAJ
Carnegie Mellon University; Meta AI
speech recognitionvideo understanding
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
7,983
 
H-index
40
 
i10-index
120
 
Publications
20
 
Co-authors
128
list available
Contact
CVOpen ↗
Publications
6 items
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
2026
Cited
0
Equipping LLM with Directional Multi-Talker Speech Understanding Capabilities
2026
Cited
0
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
2025
Cited
0
Multi-Channel Differential ASR for Robust Wearer Speech Recognition on Smart Glasses
2025
Cited
0
Embodied AI Agents: Modeling the World
2025
Cited
0
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition
2025
Cited
0
Resume (English only)
Co-authors
128 total
Alexander Waibel
Alexander Waibel
Carnegie Mellon, KIT, Karlsruhe Institute of Technology, University of Karlsruhe
Co-author 2
Co-author 2
Co-author 3
Co-author 3
Alan W Black
Alan W Black
Professor, Language Technologies Institute, Carnegie Mellon University
Tanja Schultz
Tanja Schultz
Professor of Computer Science, University Bremen
Shruti Palaskar
Shruti Palaskar
Apple
Co-author 7
Co-author 7
Hagen Soltau
Hagen Soltau
Google DeepMind

Welcome back

Sign in to Agora

Welcome back! Please sign in to continue.

Do not have an account?