221 citations · 1k across the 103 of their papers we have counts for
19 papers · 1 filter
Mixture Density Generative Adversarial Networks
Hamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer
Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this…
Attention as a Perspective for Learning Tempo-invariant Audio Queries
Matthias Dorfer, Jan Hajič, Gerhard Widmer
Current models for audio--sheet music retrieval via multimodal embedding space learning use convolutional neural networks with a fixed-size window for the input audio. Depending on…
Automatic Chord Recognition with Higher-Order Harmonic Language Modelling
Filip Korzeniowski, Gerhard Widmer
Common temporal models for automatic chord recognition model chord changes on a frame-wise basis. Due to this fact, they are unable to capture musical knowledge about chord progres…
Genre-Agnostic Key Classification With Convolutional Neural Networks
Filip Korzeniowski, Gerhard Widmer
We propose modifications to the model structure and training procedure to a recently introduced Convolutional Neural Network for musical key classification. These modifications ena…
Improved Chord Recognition by Combining Duration and Harmonic Language Models
Filip Korzeniowski, Gerhard Widmer
Chord recognition systems typically comprise an acoustic model that predicts chords for each audio frame, and a temporal model that casts these predictions into labelled chord segm…
Psychological constraints on string-based methods for pattern discovery in polyphonic corpora
David R. W. Sears, Gerhard Widmer
Researchers often divide symbolic music corpora into contiguous sequences of n events (called n-grams) for the purposes of pattern discovery, key finding, classification, and predi…