International Audio Laboratories Erlangen

Ferienakademie 2024, Sarntal (22.09. - 04.10.2024)

Course 8: Learning with Music Signals

01_MusicRepr_Teaser 02_FourierTr_Teaser 03_MusicSync_Teaser2 04_AudioStru_Teaser 06_Teaser_BeatTempo 07_Teaser_AudioRetr


Content

The revolution in music distribution, storage, and consumption has sparked significant interest in advancing techniques for managing, analyzing, and creating music-related data. Music Information Retrieval (MIR) has emerged as a distinct research area, encompassing signal processing, machine learning, information retrieval, musicology, and digital humanities. In this seminar, we delve into technologies across these disciplines, with a focus on data-driven machine learning to make accurate predictions for unseen data. By integrating insights from traditional engineering, our aim is to enhance the understanding and interpretability of recent systems based on deep learning. Additionally, we explore how music can serve as a motivating and instructive application scenario for learning in technical fields such as signal processing and machine learning. We will also investigate how visualization can be used to represent, analyze, and work with music data. Through a holistic approach, our goal is to develop explainable hybrid models and reconsider the application and communication of recent technology in interdisciplinary research and education.

Course Requirements

In this course, we discuss a number of current research problems in music processing and music information retrieval (MIR) covering aspects from information science and audio signal processing. While we provide the necessary background information, a good understanding of general concepts in signal processing and data science (e.g., algorithms, data structures) as well as strong mathematical background is required. Furthermore, basic knowledge in music theory and a strong interest in music are extremely helpful to get enthusiastic about the field of music processing.

Course Structure

The course structure will include seminar components led by participants, brief stimulus talks by lecturers and tutors, possibly programming elements, and definitely intensive discussions and interaction among participants. Teamwork is important to us. Therefore, we will divide the participants into four groups, each assigned the task of collectively developing and presenting one topic area. Possible topics may include:

  • Music Transcription Using Deep Learning Techniques
  • Differentiable Digital Signal Processing (DDSP)
  • Data Visualization for Music Representations
  • Singing Voice Processing
  • Diffusion-Based Sound Synthesis
  • ...

A thorough preparation of participants, grounded in selected scientific literature and easily understandable presentations, will form the foundation for our discussions.

Application

If you want to be part of this great event, please apply via the Ferienakademie website until 01.05.2024.

Contact

In case of questions, please feel free to contact the coordinator or tutors:

Further Links

Cover_Mueller_FMP_Springer2021

Selected Scientific Literature

  1. Simon Schwär, Michael Krause, Michael Fast, Sebastian Rosenzweig, Frank Scherbaum, and Meinard Müller
    A Dataset of Larynx Microphone Recordings for Singing Voice Reconstruction
    Transaction of the International Society for Music Information Retrieval (TISMIR), 7(1): 30–43, 2024. PDF Demo DOI 
    @article{SchwaerKRSM_LarynxEnhancement_TISMIR,
author = {Simon Schw{\"a}r and Michael Krause and Michael Fast and Sebastian Rosenzweig and Frank Scherbaum and Meinard M{\"u}ller},
title = {A Dataset of Larynx Microphone Recordings for Singing Voice Reconstruction},
journal = {Transaction of the International Society for Music Information Retrieval ({TISMIR})},
volume = {7},
number = {1},
pages = {30--43},
year = {2024},
publisher = {Ubiquity Press},
doi = {10.5334/tismir.166},
url       = {https://transactions.ismir.net/articles/10.5334/tismir.166},
url-pdf   = {/fau/professor/mueller/teaching/2024s_sarntal/literature/2024_SchwaerKFRSM_LarynxMicSVR_TISMIR_ePrint.pdf},
url-demo = {https://audiolabs-erlangen.de/resources/MIR/LM-SVR/}
}
  2. Simon Schwär and Meinard Müller
    Multiscale Spectral Loss Revisited
    IEEE Signal Processing Letters, 30: 1712–1716, 2023. PDF DOI 
    @article{SchwaerM23_MultiScaleSpecLoss_IEEE-SPL,
author = {Simon Schw{\"a}r and Meinard M{\"u}ller},
title = {Multiscale Spectral Loss Revisited},
journal = {{IEEE} Signal Processing Letters},
year={2023},
volume={30},
pages={1712--1716},
doi = {10.1109/LSP.2023.3333205},
url-pdf = {/fau/professor/mueller/teaching/2024s_sarntal/literature/2023_SchwaerM_MultiScaleSpecLoss_IEEE-SPL.pdf}
}