66 citations · 152 across the 12 of their papers we have counts for
12 papers
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 to Read and Follow Music in Complete Score Sheet Images
Florian Henkel, Rainer Kelz, Gerhard Widmer
This paper addresses the task of score following in sheet music given as unprocessed images. While existing work either relies on OMR software to obtain a computer-readable score r…
Audio-Conditioned U-Net for Position Estimation in Full Sheet Images
Florian Henkel, Rainer Kelz, Gerhard Widmer
The goal of score following is to track a musical performance, usually in the form of audio, in a corresponding score representation. Established methods mainly rely on computer-re…
Towards Interpretable Polyphonic Transcription with Invertible Neural Networks
Rainer Kelz, Gerhard Widmer
We explore a novel way of conceptualising the task of polyphonic music transcription, using so-called invertible neural networks. Invertible models unify both discriminative and ge…
Deep Polyphonic ADSR Piano Note Transcription
Rainer Kelz, Sebastian Böck, Gerhard Widmer
We investigate a late-fusion approach to piano transcription, combined with a strong temporal prior in the form of a handcrafted Hidden Markov Model (HMM). The network architecture…
Multitask Learning for Polyphonic Piano Transcription, a Case Study
Rainer Kelz, Sebastian Böck, Gerhard Widmer
Viewing polyphonic piano transcription as a multitask learning problem, where we need to simultaneously predict onsets, intermediate frames and offsets of notes, we investigate the…
Learning to Transcribe by Ear
Rainer Kelz, Gerhard Widmer
Rethinking how to model polyphonic transcription formally, we frame it as a reinforcement learning task. Such a task formulation encompasses the notion of a musical agent and an en…
Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine Grained Audio Signal Labelling
Rainer Kelz, Gerhard Widmer
We measure the effect of small amounts of systematic and random label noise caused by slightly misaligned ground truth labels in a fine grained audio signal labeling task. The task…
An Experimental Analysis of the Entanglement Problem in Neural-Network-based Music Transcription Systems
Rainer Kelz, Gerhard Widmer
Several recent polyphonic music transcription systems have utilized deep neural networks to achieve state of the art results on various benchmark datasets, pushing the envelope on…
On the Potential of Simple Framewise Approaches to Piano Transcription
Rainer Kelz, Matthias Dorfer, Filip Korzeniowski +3
In an attempt at exploring the limitations of simple approaches to the task of piano transcription (as usually defined in MIR), we conduct an in-depth analysis of neural network-ba…
Deep Linear Discriminant Analysis
Matthias Dorfer, Rainer Kelz, Gerhard Widmer
We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preser…