Archiv der Kategorie: MIR Research

Master Thesis on Instrument Recognition

Publiziert am 27. Juli 2020 von Igor Vatolkin

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 … Weiterlesen →

Veröffentlicht unter MIR Research, Theses | Hinterlasse einen Kommentar

Two Papers Presented at WCCI 2020

Publiziert am 26. Juli 2020 von Igor Vatolkin

Two papers were presented during WCCI 2020: Vatolkin, I.: Evolutionary Approximation of Instrumental Texture in Polyphonic Audio Recordings [evaluates new features based on evolutionary approximation of instrumental texture for instrument and genre recognition] Ginsel, P., Vatolkin, I. Rudolph, G.: Analysis … Weiterlesen →

Veröffentlicht unter MIR Research, Publications | Hinterlasse einen Kommentar

New book: Applications in Statistical Computing

Publiziert am 1. November 2019 von Igor Vatolkin

The book Bauer, N., Ickstadt, K., Lübke, K., Szepannek, G., Trautmann, H., Vichi, M (Eds.): Applications in Statistical Computing: From Music Data Analysis to Industrial Quality Improvement, Springer, has recently been published. This volume presents a selection of research papers … Weiterlesen →

Veröffentlicht unter MIR Research, Publications | Hinterlasse einen Kommentar

Bachelor thesis on music genre classification with Fuzzy KNN

Publiziert am 26. Januar 2019 von Igor Vatolkin

The thesis “Philipp Ginsel: Strukturelle Komplexitätsmerkmale zur Musikgenre-Klassifikation mit Fuzzy-k-nearest-Neighbors” (Structural complexity features for music genre classification with Fuzzy-k-nearest-Neighbors, PDF in German) examines different settings for extraction of structural complexity for prediction of music genres with Fuzzy KNN. The tested … Weiterlesen →

Veröffentlicht unter MIR Research, Theses | Hinterlasse einen Kommentar

Paper accepted for EvoMUSART 2019

Publiziert am 12. Januar 2019 von Igor Vatolkin

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

Veröffentlicht unter MIR Research, Publications | Hinterlasse einen Kommentar

Journal article on music rearrangement published

Publiziert am 8. Juni 2018 von Igor Vatolkin

The article on music rearrangement is published: D. Stoller, I. Vatolkin, and H. Müller: Intuitive and Efficient Computer-Aided Music Rearrangement with Optimised Processing of Audio Transitions. Journal of New Music Research, Routledge, 47(5):416-437, 2018

Veröffentlicht unter Publications | Hinterlasse einen Kommentar

Start of the DFG-funded project on interpretable music segmentation

Publiziert am 1. Februar 2018 von Igor Vatolkin

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 →

Veröffentlicht unter MIR Research, Project News | Hinterlasse einen Kommentar

Test persons are searched

Publiziert am 15. Januar 2018 von Igor Vatolkin

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.

Veröffentlicht unter MIR Research | Hinterlasse einen Kommentar

Job offer for a student assistant

Publiziert am 18. Dezember 2017 von Igor Vatolkin

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 →

Veröffentlicht unter MIR Research, SIGMA | Hinterlasse einen Kommentar

AMUSE support of Java 1.8 and RapidMiner 5

Publiziert am 24. September 2017 von Igor Vatolkin

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 →

Veröffentlicht unter AMUSE & MIR Software, MIR Research | Hinterlasse einen Kommentar