Study

Our group offers courses for bachelor and master degrees in computer science and digital humanities, topics for student and PhD theses, and research opportunities for PostDocs.

Current courses (summer term 2024)

Music Information Retrieval (Lecture + Exercise), Wed 14-18h­­

The digital revolution in music distribution, storage, and consumption is leading to a great demand for automated tools to organize, navigate, retrieve, and analyze large music databases. At the same time, such techniques are also of great importance for computational musicology as a subfield of the "Digital Humanities." In particular, music audio recordings pose challenges for the development of algorithms. As a result, the field of Music Information Retrieval (MIR) has developed into an independent research area at the intersection of different disciplines such as signal processing, information retrieval, machine learning, musicology, and the digital humanities. This course introduces the field of MIR. It teaches fundamentals of music representations (especially audio signals) and music theory concepts. A core focus is on audio signal processing algorithms, especially time-frequency transformations, as well as selected machine learning methods. Furthermore, the lecture gives an overview of MIR tasks (e. g., harmony analysis & chord recognition, beat tracking & tempo estimation, structure analysis, genre & style classification), of which selected applications are considered in depth. Finally, we address the challenges of preparing and annotating large music corpora and the application of MIR algorithms for analyzing such corpora in the context of digital humanities and computational musicology.

Contents:

This lecture introduces the research field of Music Information Retrieval (MIR), focussing on the following topics:

• Music representations (graphical, symbolic, audio), basic music theory concepts,
• Audio signal processing (esp. time-frequency transformations, variants of the Fourier transform), selected machine learning techniques
• Overview and in-depth study of individual MIR tasks (e.g., harmony analysis/chord recognition, beat tracking/tempo, structure analysis, genre/style classification)
• Data preparation/annotation and corpus analysis for digital humanities/musicology

Details:

• Lecture slot: Wednesday 14-16 h
• Exercise slot: Wednesday 16-18 h
• Place: Seminar room 00.001 (ZPD building)
• SWS: 2 + 2 (Lecture + Exercise)
• Language: English
• Credits: 5 ECTS
• Types of Examination: Oral, German or English

Study programs:

• MSc Computer Science
• MSc xtAI
• MSc LuRI
• MA Digital Humanities

Prerequisites (MSc Computer Science / xtAI):

• Very good mathematical foundations
• Advanced programming skills in Python
• Basic knowledge of deep learning techniques
• Basic knowledge in reading music (treble and bass clef)

Prerequisites (MA Digital Humanities):

• Good mathematical foundations
• Basic programming skills in Python
• Basic understanding of digital editions and corpus analysis 
• Basic knowledge of deep learning techniques
• Basic knowledge in reading music (treble and bass clef)

Special knowledge in music theory is not necessary, but will be taught in the lecture.

Please register at this WueCampus course room!­

---

Previous courses (Winter term 2023/24)

Music transcription (Seminar BA Dig. Humanities)­­

This seminar introduces algorithmic techniques for automatic music transcription techniques from audio and image sources. Students will explore different music representations, delve into musical features, and gain insights into the subtasks involved in transcription systems. They will have the opportunity to experiment with basic transcription algorithms.

Intended learning outcomes:

Students possess a solid foundation in music transcription systems. They are able to to apply these techniques for analyzing musical sources in the field of musicological research.

Details:

• Lecturer: Lele Liu
• Time: Tuesday 10-12 h
• Place: Room 02.002, ZPD building
• SWS: 2
• Language: English
• Credits: 5 ECTS
• Types of Examination: tba

Study programs:

• BA Digital Humanities

Prerequisites:

• Basic programming skills in Python
• Basic knowledge in reading music (treble and bass clef)

---

Computational Audio and Music Analysis (Seminar MA Dig. Humanities)­­

This seminar focuses on the quantitative analysis of non-textual data, especially symbolic music data and audio image data. Algorithms for the analysis of such data will be presented, applied to different music datasets, and the benefits for musicological research will be discussed. The seminar puts a focus on the use of comprehensive archives of music data for corpus analysis.

Intended learning outcomes:

Students have a basic knowledge of algorithmic procedures for analyzing audio and music data and their use for quantitative analysis. They are able to prepare datasets, apply algorithms to them, and present results to an interdisciplinary audience.

Details:

• Lecturer: Christof Weiß
• Time: Wednesday 10-12 h
• Place: Room 02.002, ZPD building
• SWS: 2
• Language: English (or German)
• Credits: 5 ECTS
• Types of Examination: tba

Study programs:

• MA Digital Humanities

Prerequisites:

• Good mathematical foundations
• Basic programming skills in Python
• Basic understanding of digital editions and corpus analysis 
• Basic knowledge of deep learning techniques
• Basic knowledge in reading music (treble and bass clef)

---

Music Processing (Seminar MSc Computer Science), Wed 14-16h­­

https://wuecampus.uni-wuerzburg.de/moodle/course/view.php?id=62685

The digital revolution in music distribution, storage, and consumption is leading to a great demand for automated tools to organize, navigate, retrieve, and analyze large music databases. Music recordings, which are available as audio data, pose challenges for the development of algorithms. In this context, music processing is often based on signal processing techniques, but more and more employs machine-learning techniques with success. In this seminar, based on prior knowledge of signal processing, current deep-learning techniques for music processing will be acquired on the basis of selected publications. This includes tasks such as harmony analysis / chord recognition, beat tracking / tempo estimation, structure analysis or genre / style classification as well as techniques such as Convolutional and Recurrent Neural Networks, U-Nets, Autoencoders or Transformers.

Contents:

The seminar covers current topics in music processing, in particular technical approaches to the analysis and generation of symbolic music data (music notation), music recordings (audio), and possibly related audio data (speech, environmental sounds). Based on basic signal processing techniques as taught in the lecture Music Information Retrieval, the seminar focuses on deep-learning techniques for music and audio analysis. Students need to investigate a research paper, possibly reimplement its algorithms, and present the approach in words (presentation) and in writing (term paper).

Details:

• Lecturers: Lele Liu and Christof Weiß
• Time: Wednesday 14-16 h
• Place: Room 02.002, ZPD building
• SWS: 2
• Language: English
• Credits: 5 ECTS
• Types of Examination: Oral presentation and written summary (term paper)

Study programs:

• MSc Computer Science
• MSc XtAI
• MA Digital Humanities

Prerequisites:

• Successful participation in the lecture Music Information Retrieval
• Very good mathematical foundations
• Advanced programming skills in Python
• Advanced knowledge of deep learning techniques
• Basic knowledge in reading music (treble and bass clef)

Application Procedure:

If you are interested in participating in this seminar, please write a short application mail to ch@informatik.uni-wuerzburg.de including

• Your study program
• Successful participation in the MIR lecture (SS2023) yes/no
• A short motivation (2-3 sentences) stating why you want to do this seminar and what topic in music processing you are interested in.

 

---