Archiv der Kategorie: MIR Research
Paper accepted for EvoMUSART 2019
The paper on evolutionary multi-objective training set selection is accepted for EvoMUSART 2019: I. Vatolkin and D. Stoller: Evolutionary Multi-Objective Training Set Selection of Data Instances and Augmentations for Vocal Detection. EvoMUSART 2019, Leipzig, 2019
Start of the DFG-funded project on interpretable music segmentation
Today, the DFG-funded project “Evolutionary optimisation for interpretable music segmentation and music categorisation based on discretised semantic metafeatures” is started. The main goal of the project is to develop new methods for the extraction of interpretable structural information of audio … Weiterlesen
Test persons are searched
We search for test persons with basic skills in jazz and improvisation, either guitar or piano players (1.5 hour experiment, 20€). Details in German are here.
Job offer for a student assistant
For the project funded by the German Research Foundation, Evolutionary Optimisation of Music Categorisation based on Complex Structure Analysis of Audio Signals, a position as a student assistant (8 hours per week) is offered at the Chair of Algorithm Engineering, … Weiterlesen
AMUSE support of Java 1.8 and RapidMiner 5
Two recent updates (thanks to Frederik Heerde!): – AMUSE can be started now with Java 1.8 (in the older version, using of Java 1.8 led to problems for classification with trained models). – Integrated RapidMiner library was updated to version … Weiterlesen
Bachelor thesis on optical recognition of bagpipe notation
The thesis “Andreas Jöbges: Optische Erkennung von Dudelsacknotation” (Optical recognition of bagpipe notation, PDF in German) presents a system which produces digital score in “BWW” format from scanned music pieces with the help of neural networks trained for the recognition … Weiterlesen
User study on playlist generation
E-Services Research Group, TU Dortmund currently conducts a study about creating music playlists and would like to invite you to participate in an online experiment. The experiment takes about 10-15 minutes. You will be asked to create a short playlist … Weiterlesen
Two papers accepted for UMAP and AES
The following papers were accepted: Kamehkhosh, I. and Jannach, D.: User Perception of Next-Track Music Recommendations. UMAP 2017, Bratislava, 2017 [describes a user case study on the evaluation of different algorithms for playlist generation with regard to perceived quality] Scholz, … Weiterlesen
Two papers accepted for EvoMUSART
F. Ostermann, I. Vatolkin, G. Rudolph: Evaluation Rules for Evolutionary Generation of Drum Patterns in Jazz Solos. Proceedings of the 6th International Conference on Computational Intelligence in Music, Sound, Art and Design (EvoMUSART 2017), Amsterdam, 2017 I. Vatolkin: Generalisation Performance … Weiterlesen
Bachelor thesis on vocal recognition
The thesis “Florian Scholz: Gesangserkennung in polyphonen Musikaufnahmen” (Vocal recognition in polyphonic music recordings, PDF in German) compares several methods for supervised recognition of vocals in music tracks. In particular, experiments with training and test sets of different genres are … Weiterlesen