This class covers basics and selected applications in the areas of intelligent audio and music analysis. After completing the class, students are enabled to independently investigate topics dealing with the analysis of acoustic data and pattern mining therein and apply machine learning and information retrieval methods to recorded audio for extraction or deduction of semantic information.

Selected topics from the areas of acoustic signal processing, auditory scene analysis, and music information retrieval are presented and discussed, comprising the following:

- Fundamentals of audio processing, analysis, and description
- Audio event detection and classification
- Detection and tracking of musical events
- Tracking of musical concepts (e.g., beats, meter, key)
- Instrument detection and transcription
- Real-time tracking of audio events
- Music genre classification and tagging
- Multi-modality in semantic music description
- Music retrieval and recommendation

Topics are contextualized historically, giving an overview of the development from hand-crafted features to recent deep learning based methods, including convolutional and recurrent neural networks. Emphasis is given to aspects of evaluation, such as used metrics and ground truth construction. Understanding of theoretical concepts is deepened through accompanying applied lab exercises.

ECTS Breakdown: 3.0h = 4.5 ECTS = 112.5 hours

• 20.0h – lectures

• 66.5h – practical tasks

• 25.0h – preparation for examination

•  1.0h – written examination

• 3 practical tasks and a written exam at the end of the semester. 
• Each task, as well as the exam, contribute 25% to the final grade. 
• On each task, at least 30% of maximum points need to be achieved to pass.