Session

Speech Processing 2

Day / Time: 20.03.2025, 14:00-15:40
Type: Regulare Lecture

Session chair

Contributions

14:00 - 14:20
Temporal Training Certificates in Crowdsourcing Multi-Dimensional Speech Quality Assessment
Kirill Shchegelskiy⁩, Benedikt Schuh, Sebastian Möller
14:20 - 14:40
The future of speech quality evaluation in the presence of AI based implementations
Hans Wilhelm Gierlich
14:40 - 15:00
A Real-time Objective Speech Analysis Tool for Analysis of Impaired Speech
Karolin Krüger, Patricia Weede, Gerhard Schmidt
15:00 - 15:20
Comparison of reference-based and single-ended prediction models for perceived listening effort
Jan Reimes, Rainer Huber, Jan Rennies-Hochmuth
15:20 - 15:40
Trainable encoders for robust and stable speech enhancement
Peter Balazs, Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler