221 citations · 1k across the 103 of their papers we have counts for
11 papers · 1 filter
Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation
Lukáš Samuel Marták, Rainer Kelz, Gerhard Widmer
This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundame…
Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries
Lukáš Samuel Marták, Rainer Kelz, Gerhard Widmer
We introduce a novel way to incorporate prior information into (semi-) supervised non-negative matrix factorization, which we call differentiable dictionary search. It enables gene…
Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers
Khaled Koutini, Shahed Masoudian, Florian Schmid +3
The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale dataset…
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
Florian Schmid, Khaled Koutini, Gerhard Widmer
Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the abili…
Cadence Detection in Symbolic Classical Music using Graph Neural Networks
Emmanouil Karystinaios, Gerhard Widmer
Cadences are complex structures that have been driving music from the beginning of contrapuntal polyphony until today. Detecting such structures is vital for numerous MIR tasks suc…
Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier
Francesco Foscarin, Katharina Hoedt, Verena Praher +2
Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-freque…