64 citations · 322 across the 45 of their papers we have counts for
15 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…
Defending a Music Recommender Against Hubness-Based Adversarial Attacks
Katharina Hoedt, Arthur Flexer, Gerhard Widmer
Adversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence mechanisms. We present a ne…
Improving Real-time Score Following in Opera by Combining Music with Lyrics Tracking
Charles Brazier, Gerhard Widmer
Fully automatic opera tracking is challenging because of the acoustic complexity of the genre, combining musical and linguistic information (singing, speech) in complex ways. In th…
On-Line Audio-to-Lyrics Alignment Based on a Reference Performance
Charles Brazier, Gerhard Widmer
Audio-to-lyrics alignment has become an increasingly active research task in MIR, supported by the emergence of several open-source datasets of audio recordings with word-level lyr…
On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples
Verena Praher, Katharina Prinz, Arthur Flexer +1
Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic ide…