SIGMA #60

The program of the 60th SIGMA meeting on 10.07.2025, 14:00-16:10, which takes place at the RWTH Aachen, Chair for Artificial Intelligence Methodology, Theaterstr. 35-39, Room 325, and online (please send an email to igor.vatolkin [at] rwth-aachen.de if you wish to get the Zoom link):

14:00-14:05 Welcome greetings

14:05-14:25 Master’s thesis (proposal)
Polina Kozarovytska: Beat Tracking for Genre-Specific Datasets Obtained by Clustering

14:25-14:45 Master’s thesis (proposal)
Philipp Selz: Hierarchical Diffusion Models to Generate Synthetic Training Data for Chord Recognition

14:45-15:05 Master’s thesis (proposal)
Malte Schörken: Extending Evolutionary Approximation of Polyphonic Music via Multi-Objective Optimisation

15:05-15:25 Master’s thesis (proposal)
Anmol Bhardwaj: A Comparative Study of Feature Representations for CNN- based Music Segmentation by Boundary Type

15:25-15:50 Research preview
Justin Dettmer: Optimising Spectrogram Parameters for Musical Instrument Recognition

15:50-16:10
Music data analysis lecture at TU Dortmund; conferences and calls; miscellaneous; next meeting

Veröffentlicht unter SIGMA | Schreib einen Kommentar

Paper with Guidelines for Multimodal Datasets Published at TISMIR

M. Gotham, B. Bemman, and I. Vatolkin: Towards an ‘Everything Corpus’: A Framework and Guidelines for the Curation of More Comprehensive Multimodal Music Data. Transactions of the International Society for Music Information Retrieval, 8(1), pp. 70-92.

Abstract: Current state-of-the-art methods for instrument and pitch detection in polyphonic music often require large datasets and long training times; resources which are sparse in the field of music information retrieval, presenting a need for unsupervised alternative methods that do not require such prerequisites. We present a modification to an evolutionary algorithm for polyphonic music approximation through synthesis that uses spectral information to initialise populations with probable pitches. This algorithm can perform joint instrument and pitch detection on polyphonic music pieces without any of the aforementioned constraints. Sets of tuples of (instrument, style, pitch) are graded with a COSH distance fitness function and finally determine the algorithm’s instrument and pitch labels for a given part of a music piece. Further investigation into this fitness function indicates that it tends to create false positives which may conceal the true potential of our modified approach. Regardless of that, our modification still shows significantly faster convergence speed and slightly improved pitch and instrument detection errors over the baseline algorithm on both single onset and full piece experiments.

Veröffentlicht unter MIR Research, Publications | Schreib einen Kommentar

A Workshop for Live Coding and Instruments (19-20.06.2025 at TU Dortmund)

Write yourself an Orchestra

A workshop for live coding and instruments.

On the occasion of the 25th anniversary of the ensemble for contemporary chamber music at the TU Dortmund, Niklas Reppel and Alicia Champlin (hailing from Toplap Barcelona) are offering a live coding workshop. In live coding, the music already emerges during the programming  process. The source code is presented to the audience, the motto is „show us your screens!“.

In this workshop, live coders and instrumental musicians meet to discover the interactions
between music and code. The workshop concludes with a concert where the freshly  composed  results will be presented.

No previous programming knowledge required. For instrumentalists, sight reading
skills would be helpful but are not strictly necessary.

Dates: Thursday, June 19th and Friday, June 20th, from 2 p.m. to 6 p.m.
Location: Dortmund University of Applied Sciences, Max-Ophüls-Platz 2, 44139 Dortmund
Final presentation: Friday, 8 p.m., Studio 215, Dortmund University of Applied Sciences, Max-Ophüls-Platz 2, 44139 Dortmund
Lecturers: Niklas Reppel and Alicia Champlin

Registration is required by June 13th, 2025, with Dr. Maik Hester:
neuekammermusik.unimusik [AT] tu-dortmund.de

Further information:
https://unimusik.tu-dortmund.de/ensembles/ensemble-fuer-neue-kammermusik/abschlusskonzert-live-scoring-on-a-human-scale-50195
https://see.ellipsenpark.de/w/xdKmBqGsJUtTwk74REXnwG
https://github.com/the-drunk-coder/megra.rs

 

Veröffentlicht unter Events | Schreib einen Kommentar

SIGMA #59

The program of the following 59th SIGMA meeting on 05.03.2025, 14:00-16:00, which takes place at the Chair of Algorithm Engineering, Deparment of Computer Science, TU Dortmund, Otto-Hahn-Str. 14, room 202, and online (please send an email to igor.vatolkin [at] rwth-aachen.de if you wish to get the Zoom link):

14:00-14:05 Welcome greetings

14:05-14:35 Master’s thesis (proposal)
Andreas Romann: Investigating Hierarchy Design for Multi-Label Music Instrument Recognition

14:35-15:05 Research study
Jonas Kramer: Using Large Language Models as Fitness Functions in Evolutionary Algorithms for Music Generation

15:05-15:40 Research study
Claus Weihs/Igor Vatolkin: First Ideas for the Identification of the Most Relevant Audio Features for Musical Genre Recognition with Optimal Decision Trees

15:40-16:00 Conferences and calls, teaching activities, miscellaneous, next meeting

Veröffentlicht unter SIGMA | Schreib einen Kommentar

SIGMA #58

The program of the following 58th SIGMA meeting on 15.11.2024, 14:00-16:00, which takes place at the Institute of Communication Acoustics, Ruhr-Universität Bochum, RUB building ID, room ID 04/413, and online (please send an email to igor.vatolkin [at] rwth-aachen.de if you wish to get the Zoom link):

14:00-14:05 Welcome greetings

14:05-14:45 PhD thesis (results)
Johannes Gauer (presented by Rainer Martin and Anil Nagathil): Audio Signal Processing Methods for the Enhancement of Music Perception in Cochlear Implant Listeners

14:45-15:25 Conference study
Anil Nagathil: DNN-based Approximation of Auditory Models for Normal and Impaired Hearing: Towards Model-based Hearing Loss Compensation

15:25-15:50 Master’s thesis (results)
Kaiteng Jiang: Multimodal Self-supervised Music Genre Classification with Audio and Lyrics

15:50-16:00 Conferences and calls, teaching activities, miscellaneous, next meeting    

Veröffentlicht unter SIGMA | Schreib einen Kommentar

Call for Papers: EvoMUSART 2025

The 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) will take place on 23-25 April 2025, as part of the evo* event.

EvoMUSART webpage: www.evostar.org/2025/evomusart/
Extended submission deadline: 15 November 2024
Conference: 23-25 April 2024

EvoMUSART is a multidisciplinary conference that brings together researchers who are working on the application of Artificial Neural Networks, Evolutionary Computation, Swarm Intelligence, Cellular Automata, Alife, and other Artificial Intelligence techniques in creative and artistic fields such as Visual Art, Music, Architecture, Video, Digital Games, Poetry, or Design. This conference gives researchers in the field the opportunity to promote, present and discuss ongoing work in the area.

Submissions must be at most 14 pages long, excluding references, in Springer LNCS format. Each submission must be anonymized for a double-blind review process.

Accepted papers will be presented orally or as posters at the event and included in the EvoMUSART proceedings published by Springer Nature in a dedicated volume of the Lecture Notes in Computer Science series.

More information on the submission process and the topics of EvoMUSART: www.evostar.org/2025/evomusart/

Flyer of EvoMUSART 2025: http://www.evostar.org/2025/flyers/evomusart

Veröffentlicht unter Conferences & Calls | Schreib einen Kommentar

Bachelor Thesis on the Multimodal AMUSE Extension

Clara Pingel’s bachelor thesis, titled „Erweiterung von AMUSE zur Verarbeitung mehrerer Modalitäten“ (Extension of AMUSE to Process Multiple Modalities, PDF in German) focuses on the further development of the AMUSE framework. The goal of the thesis was to extend the framework to process not only audio but also symbolic data to improve the classification of music pieces. The thesis specifically addresses the integration of jSymbolic for extracting symbolic features from MIDI files and the adaptation of the graphical user interface to the new functionality. The class structure was modified to prepare for future integrations of other modalities.

Veröffentlicht unter Theses | Schreib einen Kommentar

PhD and PostDoc positions on „Music Processing for Cochlear Implants“

The Institute of Communication Acoustics at Ruhr University Bochum, Germany, has open positions for a doctoral researcher and a post-doctoral researcher in the field of music processing for cochlear implants, which are funded by the German Research Foundation (DFG).

The project operates at the intersection of signal processing, machine learning, and hearing science, and aims to develop novel front-end music processing algorithms and optimization procedures based on auditory models and user feedback.

The positions will be supervised by Prof. Dr.-Ing. Rainer Martin and Dr.-Ing. Anil Nagathil.

The application deadline is August 12, 2024. The intended start date is October 1, 2024.

For more detailed information about the positions and application requirements, please see below.

Doctoral researcher:
https://jobs.ruhr-uni-bochum.de/jobposting/a90cbcfa7d5089b10131ce07d2c0f0543dd4d9780?ref=homepage

Post-doctoral researcher:
https://jobs.ruhr-uni-bochum.de/jobposting/e035dabad62700e75763c4c7b325d532360a8e240?ref=homepage

Please feel free to forward these advertisements to suitable and interested students and researchers.

Veröffentlicht unter Jobs | Schreib einen Kommentar

SIGMA #57

The program of the following 57th SIGMA meeting on 11.07.2024, 16:00-18:15, which takes place at the Chair for AI Methodology, RWTH Aachen, Theaterstr. 35-39, room 325, and online (please send an email to igor.vatolkin [at] rwth-aachen.de if you wish to get the Zoom link):

16:00-16:05 Welcome greetings

16:05-16:35 Bachelor’s thesis (introduction)
Philipp Springer: Using Siamese Neural Networks to Evaluate the Similarity of Polyphonic Audio Recordings

16:35-17:05 Conference study
Leonard Fricke: Adaptation and Optimization of AugmentedNet for Roman Numeral Analysis Applied to Audio Signals

17:05-18:05 Master’s thesis (results)
Johannes Mertens: Results of Empirical Studies on the Perception of Intervals and Triads with Historic Temperaments
(with an introductory listening demo by Martin Ebeling)

18:05-18:15 Conferences and calls, teaching activities, miscellaneous, next meeting

Veröffentlicht unter SIGMA | Schreib einen Kommentar

Lecture @ RWTH Aachen by Nikita Braguinski: Life-Like Artificial Music: Understanding the Impact of AI on Musical Thinking

Life-Like Artificial Music: Understanding the Impact of AI on Musical Thinking
June 5, 17:00-18:30
RWTH Aachen. Käte Hamburger Kolleg “Cultures of Research”
Theaterstraße 75, 52062 Aachen
Online participation is also possible: https://khk.rwth-aachen.de/event/evening-lecture-ss24-4/

This lecture explores the impact of machine learning on the future of music research and theory.  It argues that AI-generated music poses a deep challenge for existing theories: AI systems can  learn to imitate musical styles without receiving any information about human music theory concepts, raising questions about the validity of those concepts. Additionally, music-generating  AI systems can be trained on audio directly, bypassing notation, while human music theory  almost always works with notation as a simplified and abstracted proxy.

As an example of the conceptual challenges and shifts that now arise in music research, the talk  examines a recent paper that compares Western music theory concepts with structures that  emerge in a machine learning model trained on musical notation. While the paper finds  similarities between the two, the talk argues that the machine learning system’s output is still  influenced by human biases and choices in the training data and model architecture – and that  this influence may in fact be unavoidable.

Finally, the talk argues that while AI may be able to generate novel structures for analyzing
music, their applicability to human music theory and practice may prove to be extremely limited  due to the differences between human cognition and machine learning. Overall, the talk raises  questions about the future potential for AI to disrupt human theory-making – and not only in the  discipline of musicology.

No knowledge of musicological concepts is required for understanding the presentation and participating in the discussion.

Dr. Nikita Braguinski is a 2023-2024 Fellow at the Käte Hamburger Kolleg “Cultures of Research” at RWTH Aachen University. In his work he currently concentrates on the possible impact of machine learning and big online listening datasets on the future of music research. His book “Mathematical Music. From Antiquity to Music AI” (Routledge, 2022) was translated into Korean, receiving the Sejong book prize in 2023. He was a Fellow at Harvard University, a Visiting Scholar at the University of Cambridge, and a Researcher at Humboldt University of Berlin with funding from the Volkswagen Foundation. In 2023, he co-convened, together with Eamonn Bell and Miriam Akkermann, the ZiF Bielefeld Visiting Research Group “The Future of Musical Knowledge in the Age of Machine Learning”.

Veröffentlicht unter Events | Schreib einen Kommentar