Course on music data analysis at TU Dortmund

Publiziert am 1. Oktober 2016 von Igor Vatolkin

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.

Veröffentlicht unter Teaching Activities | Schreib einen Kommentar

Bachelor thesis on the impact of cepstral features for emotion recognition

Publiziert am 13. Juli 2016 von Igor Vatolkin

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.

Veröffentlicht unter MIR Research, Theses | Schreib einen Kommentar

Diploma thesis on feature processing for classification of instruments and genres

Publiziert am 7. Juli 2016 von Igor Vatolkin

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.

Veröffentlicht unter MIR Research, Theses | Schreib einen Kommentar

Invited talk by Prof. Gerald Langner

Publiziert am 9. Juni 2016 von Igor Vatolkin

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.

Veröffentlicht unter (Guest) Talks, Events | Schreib einen Kommentar

Music data analysis book can be pre-ordered now!

Publiziert am 20. Mai 2016 von Igor Vatolkin

Weihs, C., Jannach, D., Vatolkin, I., Rudolph, G. (Eds.): Music data analysis: foundations and applications.

https://www.crcpress.com/Music-Data-Analysis-Foundations-and-Applications/Weihs-Jannach-Vatolkin-Rudolph/p/book/9781498719568

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.

Features:

  • Covers, in a comprehensive fashion, the foundations of music data analysis as well as advanced material
  • Contains all required introductory material in music, statistics and data mining
  • Shows various applications of music data analysis, including transcription and segmentation as well as chord and harmony, instrument and tempo recognition
  • Discusses implementation aspects of music data analysis, including architecture, user Interface and hardware
    • Veröffentlicht unter Publications | Schreib einen Kommentar

    Proseminars on music data analysis and computational intelligence in games

    Publiziert am 15. Mai 2016 von Igor Vatolkin

    In winter term 2016/2017, two proseminars will take place at Chair of Algorithm Engineering, TU Dortmund:

  • „Actual challenges in music data analysis“ The topics for student talks and works should represent various MIR research areas and will be selected from the proceedings of ISMIR 2015
  • „Computational intelligence in games“ The topics for student talks and works will be selected mainly from the proceedings of CIG 2015 and GECCO 2015
    • Veröffentlicht unter Teaching Activities | Schreib einen Kommentar

    UMAP paper accepted

    Publiziert am 16. April 2016 von Igor Vatolkin

    Jannach, D., Kamehkhosch, I., Bonnin, G.: Biases in Automated Music Playlist Generation: A Comparison of Next-Track Recommending Techniques, User Modeling, Adaptation and Personalization (UMAP 2016), Halifax, CA, 2016

    In this work, the results of a multi-metric comparison of different academic approaches and a commercial playlisting service (of The Echo Nest) are reported. The results show that all tested techniques generate playlists with certain biases, e.g., towards very popular tracks, and often create playlists continuations that are quite different from those that are created by real users.

    Veröffentlicht unter Publications | Schreib einen Kommentar

    Master thesis on lyrics finished

    Publiziert am 10. April 2016 von Igor Vatolkin

    Florian Treinat: Verwendung von Lyrics zur Generierung von Musik-Playlisten (Application of lyrics for generation of music playlists) (supervisors: Dietmar Jannach, Iman Kamehkhosh, e-Services Research Group, TU Dortmund)

    The goal of this work was to improve the quality of music recommendations with the help of lyrics. The proposed approaches are based on (a) the textual similarity and (b) the conveyed sentiment of lyrics. The results show that lyrics-based techniques are more efficient when the seed tracks (e.g., the tracks from the recent listening history of the user) are thematically related or sentimentally homogeneous.

    Veröffentlicht unter Theses | Schreib einen Kommentar

    Master thesis on Twitter music data finished

    Publiziert am 1. Februar 2016 von Igor Vatolkin

    Mike Gösker: #nowplaying: Analyse musikbezogener Twitterdaten (Analysis of music-related Twitter data) (supervisors: Dietmar Jannach, Lukas Lerche, e-Services Research Group, TU Dortmund)

    In his master’s thesis Mike Gösker implemented and evaluated a set of techniques to generate music track recommendations based on user posts and profiles from the social networking service Twitter. The recommendation strategies exploit temporal characteristics of the social media posts and are compared with baseline techniques that use popularity and neighborhood information.

    Veröffentlicht unter Theses | Schreib einen Kommentar

    Bachelor thesis on generation of drum accompaniment to improvised Jazz solos

    Publiziert am 5. Dezember 2015 von Igor Vatolkin

    The goal of the thesis (PDF in German) was to develop a system for the automatic generation of drum accompaniment to improvised Jazz solos. This is solved by means of an evolutionary algorithm. A list of rules is defined for the evaluation of percussive patterns with regard to music and Jazz theory. Furthermore, the thesis provides an overview of related research works.

    Veröffentlicht unter MIR Research, Theses | Schreib einen Kommentar