• Publications
  • Influence
Learning in the Presence of Concept Drift and Hidden Contexts
TLDR
A family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear are described, including a heuristic that constantly monitors the system's behavior.
Learning in the presence of concept drift and hidden contexts
TLDR
A family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear are described, including a heuristic that constantly monitors the system's behavior.
Deep Linear Discriminant Analysis
TLDR
Deep Linear Discriminant Analysis is introduced which learns linearly separable latent representations in an end-to-end fashion and produces competitive results on MNIST and CIFAR-10 and outperforms a network trained with categorical cross entropy on a supervised setting of STL-10.
On the Potential of Simple Framewise Approaches to Piano Transcription
TLDR
It is shown that it is possible, by simple bottom-up frame-wise processing, to obtain a piano transcriber that outperforms the current published state of the art on the publicly available MAPS dataset -- without any complex post-processing steps.
Evaluating Rhythmic descriptors for Musical Genre Classification
TLDR
This article considers a specific set of rhythmic descriptors for which it provides procedures of automatic extraction from audio signals and concludes on the particular relevance of the tempo and a set of 15 MFCC-like descriptors.
Improvements of Audio-Based Music Similarity and Genre Classificaton
TLDR
It is shown that spectral similarity with complementary information from fluctuation patterns including two new descriptors derived from them can be combined to form genre classification patterns.
Joint Beat and Downbeat Tracking with Recurrent Neural Networks
TLDR
A recurrent neural network operating directly on magnitude spectrograms is used to model the metrical structure of the audio signals at multiple levels and provides an output feature that clearly distinguishes between beats and downbeats.
CP-JKU SUBMISSIONS FOR DCASE-2016 : A HYBRID APPROACH USING BINAURAL I-VECTORS AND DEEP CONVOLUTIONAL NEURAL NETWORKS
TLDR
This report describes the 4 submissions for Task 1 (Audio scene classification) of the DCASE-2016 challenge of the CP-JKU team and proposes a novel i-vector extraction scheme for ASC using both left and right audio channels and a Deep Convolutional Neural Network architecture trained on spectrograms of audio excerpts in end-to-end fashion.
Tracking Context Changes through Meta-Learning
  • G. Widmer
  • Computer Science
    Machine Learning
  • 1 June 1997
TLDR
A general two-level learning model is presented that effectively adjusts to changing contexts by trying to detect (via ‘meta-learning’) contextual clues and using this information to focus the learning process.
...
...