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
The program of the following 45th SIGMA meeting on 18.12.2018, 16:00-18:00, which takes place at the Chair of Algorithm Engineering, Deparment of Computer Science, TU Dortmund, Otto-Hahn-Str. 14, room 202:
16:00-16:10 Welcome greetings
16:10-16:55 Master thesis
Ben Wilkes: Analysis of Image-, Text- and Audio-based Features for Classification of Music Genres
16:55-17:40 Guest talk
Daniel Stoller, Queen Mary University of London: Techniques for Improving Singing Voice Separation
17:40-17:50 Miscellaneous, next meeting
The program of the following 44th SIGMA meeting on 20.09.2018, 14:00-16:00, which takes place at the Chair of Computational Statistics, TU Dortmund, Vogelpothsweg 87, room 217b:
14:00-14:10 Welcome greetings
14:10-15:10 Guest talk
Trudie Sandrock, Stellenbosch University: Multi-label Classification of Music Data
15:10-15:30 Conference study
Igor Vatolkin: Classification of Ethnic and Western Instrument Samples
15:30-15:50 Software demo
Frederik Heerde: Extensions to Annotation Editor in AMUSE
15:50-16:00 Miscellaneous, next meeting
The program of the following 43rd SIGMA meeting on 27.07.2018, 14:00-16:00, which takes place at the Department of Music and Musicology, TU Dortmund, Emil-Figge-Straße 50, room 4307:
14:00-14:05 Welcome greetings
14:05-14:30 Master thesis
Eric Gödel: What is Open-Earness? An Online Study to Deal with Music as a Basis for a Definition
14:30-14:50 Master thesis (introduction and preliminary results)
Frederik Heerde: Construction and Evolutionary Optimisation of Fuzzy Rule Bases for Classification of Music Genres
14:50-15:10 Conference study
Iman Kamehkhosh: How Automated Recommendations Affect the Playlist Creation Behavior of Users
15:10-15:30 Conference study
Igor Vatolkin: Measurement of Robustness of Features and Classification Models on Degraded Data Sets in Music Classification
15:30-15:45 Software demo
Frederik Heerde: Extensions to Annotation Editor in AMUSE
15:45-15:55 Miscellaneous, next meeting
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
The program of the following 42nd SIGMA meeting on 04.05.2018, 14:00-16:00, which takes place at the Institute of Communication Acoustics, Ruhr-Universität Bochum, ID 2 / room 232:
14:00-14:35 Bachelor thesis
Marco Eckey: Comparison of Characteristics of Lyrics with Audio Features for Music Genre Classification
14:35-15:00 Guest talk
Roman Klinger, University of Stuttgart: Analysis of Emotions in Social Media: Chances for Collaborations in Music Data Analysis?
15:00-15:20 Study
Johannes Gauer: Binaural Spectral Complexity Reduction of Music Signals for Cochlear Implant Listeners
15:20-15:40 Study
Igor Vatolkin, Daniel Stoller: Identification of Vocals in Polyphonic Recordings
15:40-16:00 Study
Igor Vatolkin, Günter Rudolph: Classification of Ethnic and Western Instrument Samples
We would like to announce a Session „Statistical Musicology“ at the 5th European Conference on Data Analysis, July 4 – 6, 2018, in Paderborn (Germany).
The ECDA conferences are well-known for both, their theoretical and their practical contributions, on various fields of classification and data analysis. The session is open to all topics in the field. The idea is to give all statistically oriented groups in the field a forum to improve communication as well as to give us the chance to also join statistical methodology oriented sessions on supervised and unsupervised learning and data analysis in general at the conference.
Please note that abstracts have to be submitted until April 1, 2018. More information and templates can be found under: http://ecda2018.de. Accepted papers corresponding to presentations will be published in the journal „Archives of Data Science, Series A“. Full papers can be submitted until September 15, 2018.
C. Weihs and I. Vatolkin
(Session Organizers)
Within the scope of a master thesis at TU Dortmund, an online survey (in German) is currently open: https://umfragen.tu-dortmund.de/index.php/698612?lang=de
The participation time should be about 5-10 minutes and it is possible to win one of two 25€ gift vouchers for Amazon shop.
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 recordings and to improve the classification of music into genres, styles, and emotions, see also the project description in the GEPRIS database.
The course on music data analysis (in German) based on the textbook Music Data Analysis: Foundations and Applications will again take place at TU Dortmund, this time at the Department of Computer Science and during the summer term (see also the course web page from the last year).
