Prof. Dr. Emanuël Habets

Speech and Language Processing

• Voice Quality Enhancement (incl. Source Separation and Target Speaker Extraction)
• Dialog Enhancement
• Representation Learning
• Text-to-Speech
• Privacy

Spatial Audio and Acoustics

• Acoustic Signal Processing
• Spatial Audio Recording and Reproduction
• Perception and Evaluation
• Acoustic Scene Analysis (incl. Acoustic Parameter Estimation and Sound Source Localization)
• Room Geometry inference
• Virtual Acoustics

Applications

• Speech Communication
• Human-Machine Interaction
• Sound Recording and Rendering
•  Virtual and Augmented Reality

Contact:

• Email: emanuel.habets@audiolabs-erlangen.de
• Web site: https://www.audiolabs-erlangen.de/ehabets