TP2b.3

A Novel Perceptual Loss Function for Audio and Music Quality Differentiable in PyTorch

Gerald Schuller, Ilmenau University of Technology, Germany, Germany
Session:
TP2b: Perceptual and Higher Level Loss and Distance Functions for Audio and Acoustics Lecture
Track:
Speech, Image and Video Processing
Location:
Acacia
Presentation Time:
Tue, 29 Oct, 16:20 - 16:45 PT (UTC -7)
Session Co-Chairs:
Gerald Schuller, Ilmenau University of Technology and Muhammad Imran, Ilmenau University of Technology
Presentation
Discussion
Resources
No resources available.
Session TP2b
TP2b.1: Similarity Metrics for Late Reverberation
Gloria Dal Santo, Prawda Karolina, Aalto University, Finland; Sebastian Jiro Schlecht, Friedrich-Alexander-Universitat Erlangen-Nurnberg (FAU), Germany; Vesa Välimäki, Aalto University, Finland
TP2b.2: Time-Frequency Audio Similarity using Optimal Transport
Linda Fabiani, Ecole Polytechnique Fédérale de Lausanne, Switzerland; Sebastian J. Schlecht, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany; Filip Elvander, Aalto University, Finland
TP2b.3: A Novel Perceptual Loss Function for Audio and Music Quality Differentiable in PyTorch
Gerald Schuller, Ilmenau University of Technology, Germany, Germany
TP2b.4: Instrumental Timbre Transfer Based on Disentangled Representation of Timbre and Pitch
Lin Ye, Gerald Schuller, Muhammad Imran, Ilmenau University of Technology, Germany, Germany
TP2b.5: Pruning-aware Loss Functions for STOI-Optimized Pruned Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay
Reemt Hinrichs, Jörn Ostermann, Leibniz University Hannover, Germany
Contacts