The following paper was accepted for Entropy:
B. Wilkes, I. Vatolkin, and H. Müller: Statistical and Visual Analysis of Audio, Text, and Image Features for Multi-Modal Music Genre Recognition
The following paper was accepted for Entropy:
B. Wilkes, I. Vatolkin, and H. Müller: Statistical and Visual Analysis of Audio, Text, and Image Features for Multi-Modal Music Genre Recognition
For assistance during software project „Music Informatics“, a position as a student assistant (8 hours per week) is offered at the Chair of Algorithm Engineering, Department of Computer Science, TU Dortmund. Please see the full description in German.
Two new positions are available in the newly established Dortmund Systematic Musicology Lab, Technische Universität Dortmund, Germany:
For more information, please contact Prof. Dr. Hauke Egermann.
The program of the following 50th SIGMA meeting on 24.09.2021, 14:00-16:30, which takes place online
(please send an email to igor.vatolkin [at] udo.edu if you wish to get the Zoom link):
14:00-14:10 Welcome greetings + several slides on the history of SIGMA
14:10-14:40 Research study
Mark Gotham: „Representative“ examples and restrictive „rules“ in music theory
14:40-15:05 Bachelor’s thesis (intermediate results)
Felix Wolff: Optimization of the calculation of zygones in „Schuberts Winterreise Dataset“ with beat-synchronized audio features
15:05-15:15 Ongoing teachning courses, conferences and calls, miscellaneous, next meeting
15:15-16:00 Guest talk
Meinard Müller: Learning-By-Doing: Using the FMP Python Notebooks for Audio and Music Processing
16:00+ Open discussion
The program of the following 49th SIGMA meeting on 18.06.2021, 10:00-12:10, which takes place online
(please send an email to igor.vatolkin [at] udo.edu if you wish to get the Zoom link):
10:00-10:05 Welcome greetings
10:05-10:25 Conference study
Maria Heinze, Frieder Stolzenburg (Hochschule Harz): Harmony cognition by neural transformation – an analysis by EEG
10:25-10:55 Master’s thesis (results)
Fabian Ostermann: Modelling of listener music preferences with neural networks
10:55-11:15 Bachelor’s thesis (results)
Pauline Speckmann: Integration of clustering in AMUSE
11:15-11:35 Master’s thesis (introduction)
Philipp Ginsel: Distance measures for evolutionary approximation of audio data
11:35-12:00 Conference presentation + development plan
Igor Vatolkin, Philipp Ginsel: Changes in AMUSE since its presentation at ISMIR 2010 / development plan for the next years
12:00-12:10 Ongoing teachning courses, conferences and calls, miscellaneous, next meeting
The following paper was accepted for SIGIR conference:
I. Vatolkin, P. Ginsel, and G. Rudolph: Advancements in the Music Information Retrieval Framework AMUSE over the Last Decade
Before the presentation at SIGIR, we will update the user manual (the current version is available at https://github.com/AdvancedMUSicExplorer/AMUSE/blob/master/amuse/docs/user_manual.pdf)
The program of the following 48th SIGMA meeting on 15.03.2021, 14:00-16:15, which takes place online
(please send an email to igor.vatolkin [at] udo.edu if you wish to get the Zoom link):
14:00-14:05 Welcome greetings
14:05-14:40 Master’s thesis (final results)
Stephan Steup: Perception and Production of Polyrhythms: an Empiric Study
14:40-15:20 Research proposal
Nezar Dasan: Development of Automatic Proofreading for Speech to Text Applications in Arabic Language
15:20-15:40 Bachelor’s thesis (introduction)
Pauline Speckmann: Integration of Clustering in AMUSE
15:40-16:00 Master’s thesis (introduction)
Florian Scholz: Inclusion of Different Instrument Bodies for Robust Training of Neural Networks for Instrument Recognition
16:00-16:15 Ongoing teachning courses, conferences and calls, miscellaneous, next meeting
The repository of Advanced MUSic Explorer has moved to:
Two courses will take place during the winter term at TU Dortmund (web pages in German):
The thesis „Benedikt Adrian: Implementierung von hybriden Methoden zur Instrumentenerkennung in verrauschten Musikdaten“ (Implementation of Hybrid Methods for Instrument Recognition in Noisy Music Data, PDF in German) applies CNNs together with shallow classifiers for the recognition of instruments in polyphonic audio signals and measures the impact of data augmentation for the training of classification models.