On the music data analysis textbook web page, the exercises manual is now available for download.
The program of the following 37th SIGMA meeting on 19.12.2016, 14:00-16:20, which takes place at Faculty of Statistics, TU Dortmund, Mathematics Building, room M/E27
(talks on bachelor theses in German):
14:00-14:05 Welcome greetings
14:05-14:30 Bachelor thesis
Alex Runge: Analysis of energy features for prediction of emotions in music
14:30-14:55 Bachelor thesis
Philipp Hallmeier: Modelling of frequency and amplitude modulation
14:55-15:20 Bachelor thesis + Demo
Fabian Ostermann: Generation of drum accompaniment to improvised Jazz solos
15:20-15:30 Short break
15:30-15:45 Bachelor thesis
Florian Scholz: Recognition of vocals in polyphonic music recordings
15:45-16:00 ISMIR conference paper
Daniel Stoller: Analysis and classification of phonation modes in singing
16:00-16:20 Coursebook on music data analysis, teaching exercises and slides, miscellaneous, next meeting
The e-Services research group of the computer science department, TU Dortmund is conducting a user study about automated music recommendation and would like to invite you to participate in an online experiment. The experiment takes about 10 minutes. You will be asked to listen to a few song excerpts and to give feedback on them. Start the experiment here: http://bit.ly/ls13-mus. Thank you!
The textbook on music data analysis is now published.
Weihs, C., Jannach, D., Vatolkin, I., Rudolph, G. (Eds.):
Music data analysis: foundations and applications
For the list of chapters, see http://sig-ma.de/music-data-analysis-book
The GECCO 2017 Program Committee invites the submission of technical papers describing your best work in genetic and evolutionary computation. As in previous GECCO conferences, the digital entertainment technologies and arts (DETA) track invites submissions describing original work involving the use of computation in the creative arts, including design, games, and music.
Abstracts need to be submitted by January 30, 2017. Full papers are due by the non-extensible deadline of February 6, 2017. Note that only full papers can be reviewed and accepted. The abstracts allow us to prepare better for the reviewing process.
Each paper submitted to GECCO will be rigorously evaluated in a double-blind review process. The evaluation is on a per-track basis, ensuring high interest and expertise of the reviewers. Review criteria include significance of the work, technical soundness, novelty, clarity, writing quality, and sufficiency of information to permit replication, if applicable. All accepted papers will be published in the ACM Digital Library.
By submitting a paper, the author(s) agree that, if their paper is accepted, they will:
- submit a final, revised, camera-ready version to the publisher on or before the camera ready deadline,
- register at least one author to attend the conference on or before the advance registration deadline,
- attend the conference (at least one author), and
- present the accepted paper at the conference.
In September 2016, the interdisciplinary course on music data analysis based on the textbook “Music Data Analysis: Foundations and Applications” took place at the Faculty of Statistics, TU Dortmund. The course contained lectures, exercises, and an a written examination. The participated students came from several faculties including statistics, computer science, data science, signal processing, electrical engineering, and music science. The list of lecture units (in German) is available on the course web site. In future, we plan to release the slides of the course to the SIGMA website of the book.
In the thesis “Philipp Kramer: Relevanz cepstraler Merkmale für Vorhersagen im Arousal-Valence Modell auf Musiksignaldaten” (Relevance of cepstral features for predictions in arousal-valence model for music signals, PDF in German), several groups of features were analysed for the regression-based prediction of arousal and valence: cepstral, energy, timbral, harmonic/melodic, and temporal/rhythmic. Some parameters for the feature extraction were optimised, and it was shown that features from the cepstral domain belonged to the best models.
The task of the thesis “Ettiboa Adouakou: Zur Bedeutung verlaufspezifischer Merkmale bei Klassifikationsproblemen auf Musiksignaldaten” (On the meaning of time-based feature aggregation for classification of audio signal data), PDF in German) was to compare several groups of time-based feature aggregation methods (statistics, stacking, autoregressive models). Different classification methods, selected classification tasks (recognition of instruments and genres), and the variation of parameters of processing methods contributed to the study.
Prof. Dr. Gerald Langner from TU Darmstadt will give a talk “Der neuronale Code von Tonhöhe, Klang und Harmonie” (The neural code of pitch, sound, and harmony) at the Institute of Music and Music Science, TU Dortmund on 6.7.2016, 14-16 PM, Emil-Figge-Str. 50, R 4.313.
Weihs, C., Jannach, D., Vatolkin, I., Rudolph, G. (Eds.): Music data analysis: foundations and applications.
This book edited and co-authored by SIGMA members and several partners provides a comprehensive overview of music data analysis, from introductory material to advanced concepts. It covers various applications including transcription and segmentation as well as chord and harmony, instrument and tempo recognition. It also discusses the implementation aspects of music data analysis such as architecture, user interface and hardware. It is ideal for use in university classes with an interest in music data analysis. It also could be used in computer science and statistics as well as musicology.