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 of Structural Complexity Features for Music Genre Recognition
[provides an analysis of different parameters and features for structural complexity estimation applied to genre recognition]
The program of the following 47th SIGMA meeting on 19.06.2020, 14:00-16:15, which takes place online:
https://tu-dortmund.zoom.us/j/94868569943?pwd=dXJFK3dvS3VMV1lWMTVYRFBhcENpdz09
14:00-14:05 Welcome greetings
14:05-14:25 Conference study
Benjamin Lentz: Harmonic/Percussive Sound Separation and Spectral Complexity Reduction of Music Signals for Cochlear Implant Listeners
14:25-15:00 Master thesis and extended study
Marcel Koch: Identification of Effective Features for Novelty Based Music Segmentation
Igor Vatolkin: Multi-Objective Feature Selection for Music Segmentation
15:00-15:35 Master thesis and extended study
Benedikt Adrian: Implementation of Hybrid Methods for Instrument Recognition in Noisy Music Data
Igor Vatolkin: Analysis of Instrument and Timbre Features for Genre Recognition
15:35-15:55 Database demo
Fabian Ostermann: Further Development of Database with Artificial Tracks for Multiple Classification Tasks
15:55-16:15 Teachning courses in winter term, miscellaneous, next meeting
Digital Entertainment Technologies and Arts Track @ GECCO in Cancun, Mexico, July 8th-12th 2020, invites for submissions describing original work involving the use of computational intelligence techniques in the creative arts, including design, games, and music. Works of a methodological, experimental, or theoretical nature within the context of digital entertainment and its application in industry will also be considered.
Full papers of at most 8 pages (excluding references) should present original work that meets the high-quality standards of GECCO. Accepted full papers appear in the ACM digital library as part of the Main Proceedings of GECCO. For full papers, a separate abstract needs to be submitted first by January 30, 2020. Full papers are due by the non-extensible deadline of February 6, 2020.
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 on various topics at the interface of statistics and computer science. Emphasis is put on the practical applications of statistical methods in various disciplines, using machine learning and other computational methods. The book covers fields of research including the design of experiments, computational statistics, music data analysis, statistical process control, biometrics, industrial engineering, and econometrics. Gathering innovative, high-quality and scientifically relevant contributions, the volume was published in honor of Claus Weihs, Professor of Computational Statistics at TU Dortmund University, on the occasion of his 66th birthday.
Software project „Music informatics“ has started at the Chair of Algorithm Engineering, Department of Computer Science, TU Dortmund. In small groups of students, various tasks are solved, e.g., optmisation of audio feature extraction, recognition of genres and instruments, application of deep neural networks for music classification, etc.
The program of the following 46th SIGMA meeting on 21.06.2019, 16:00-18:00, which takes place at the Department of Music and Musicology, TU Dortmund, Emil-Figge-Straße 50, room 4315:
16:00-16:05 Welcome greetings
16:05-16:30 Bachelor thesis
Johannes Mertens: The tuning of the Förner-Organ in the Castle Church in Weißenfels
16:30-16:50 Master thesis
Hauke Singerhoff: Music Segmentation with Convolutional Neural Networks
16:50-17:10 Master thesis
Ben Wilkes: Analysis of Image, Text, and Audio-based Features for Music Genre Classification
17:10-17:30 Software demo
Philipp Ginsel: Extensions for Music Classification in AMUSE
17:30-17:50 Database demo
Fabian Ostermann: Artificial Music Pieces for Music Segmentation and Instrument Detection
17:50-18:00 Miscellaneous, next meeting
This year the annual autumn meeting of the AG DANK (http://www.gfkl.org/working-groups/data-analysis-numerical-classification/) will focus but not be limited to “Musical Data Analysis”. It will be hosted in Dortmund by Karsten Lübke (FOM) and Claus Weihs (TU Dortmund) on October the 10th and 11th. For further informations and/or submissions please contact karsten.luebke [at] fom.de
„Engineering meets Art“, an exhibition showing the results of a project which commemorates the 50th anniversary of the Faculty of Organic and Chemical engineering as interdisciplinary cooperation with the Faculty of Arts and Sports had been launched and will be on show at the Dortmund „U“ until 23 June 2019.
The exhibition is embedded in the diversity dialogues of the TU Dortmund, a professional meeting of different disciplines and Specialized cultures at the university. Funded by the innogy foundation for
Energy and Society gGmbH both students of the Bio and Chemical engineering and students of music and photography worked in interdisciplinary teams over two semesters and developed works of art at the interface of Art and engineering.
The insights into the unknown work areas of the respective partner faculty brought inspirational ideas, new working methods and surprising change of perspective: Dead bees learn to fly, photographic film goes getting under its skin, you can hear insulin and see sound waves.
On 15.05. there was an enthusiastic bruadcast by Stefan Keim in the program „Culture at noon“ at WDR3, which you can listen to here.
Impressions of the opening ceremony can be found here.
Information about individual objects and projects of the exhibition are to find here.
„Engineering meets Art“ will run until 23.06.2019 in the Dortmund „U“, Leonie-Reygers terrace. Admission is free.
Accompanying the exhibition is a lovingly designed catalog which we gladly hand over to you on request.
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 structural compexity characteristics comprise the progress of chords, chroma, chroma-related features, harmony, instruments, tempo/rhythm, and timbre.
Digital Entertainment Technologies and Arts GECCO track invites submissions describing original work involving the use of computational intelligence techniques in the creative arts, including design, games, and music.
The deadline for abstracts is 30.01.2019 and for full papers 06.02.2019. For more details, see call for papers.
