Deep Learning and Knowledge Integration for Music Audio Analysis (Dagstuhl Seminar 22082)

Authors Meinard Müller, Rachel Bittner, Juhan Nam, Michael Krause, Yigitcan Özer and all authors of the abstracts in this report

Thumbnail PDF


  • Filesize: 3.92 MB
  • 31 pages

Document Identifiers

Author Details

Meinard Müller
  • Friedrich-Alexander-Universität Erlangen-Nürnberg, DE
Rachel Bittner
  • Spotify - Paris, FR
Juhan Nam
  • KAIST - Daejeon, KR
Michael Krause
  • Friedrich-Alexander-Universität Erlangen-Nürnberg, DE
Yigitcan Özer
  • Friedrich-Alexander-Universität Erlangen-Nürnberg, DE
and all authors of the abstracts in this report

Cite AsGet BibTex

Meinard Müller, Rachel Bittner, Juhan Nam, Michael Krause, and Yigitcan Özer. Deep Learning and Knowledge Integration for Music Audio Analysis (Dagstuhl Seminar 22082). In Dagstuhl Reports, Volume 12, Issue 2, pp. 103-133, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Given the increasing amount of digital music, the development of computational tools that allow users to find, organize, analyze, and interact with music has become central to the research field known as Music Information Retrieval (MIR). As in general multimedia processing, many of the recent advances in MIR have been driven by techniques based on deep learning (DL). There is a growing trend to relax problem-specific modeling constraints from MIR systems and instead apply relatively generic DL-based approaches that rely on large quantities of data. In the Dagstuhl Seminar 22082, we critically examined this trend, discussing the strengths and weaknesses of these approaches using music as a challenging application domain. We mainly focused on music analysis tasks applied to audio representations (rather than symbolic music representations) to give the seminar cohesion. In this context, we systematically explored how musical knowledge can be integrated into or relaxed from computational pipelines. We then discussed how this choice could affect the explainability of models or the vulnerability to data biases and confounding factors. Furthermore, besides explainability and generalization, we also addressed efficiency, ethical and educational aspects considering traditional model-based and recent data-driven methods. In this report, we give an overview of the various contributions and results of the seminar. We start with an executive summary describing the main topics, goals, and group activities. Then, we give an overview of the participants' stimulus talks and subsequent discussions (listed alphabetically by the main contributor’s last name) and summarize further activities, including group discussions and music sessions.

Subject Classification

ACM Subject Classification
  • Information systems → Music retrieval
  • Applied computing → Sound and music computing
  • Audio signal processing
  • deep learning
  • knowledge representation
  • music information retrieval
  • user interaction and interfaces


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail