Seminar/Thesis: Automatic tagging audio databases
Machine learning methods can nowadays be very helpful to automatically collect data and build large-sized datasets. However, the retrieved datasets need to be cataloged before being further processed. The project aims at implementing a convenient algorithm for the automatic tagging of audio data retrieved from publicly available repositories.
Apply algorithms to catalog and tag automatically audio data retrieved from publicly available repositories.
- Analyse audio data from open source repositories
- Apply audio processing methods to segment and tag data stream
- Apply machine learning algorithms to automate the process
|Project type||Seminar (optional: Master thesis)|
|ECTS||2.5, 5, 7.5, default: 5|
|Period||Summer term 2021|
|Presence time||Virtual seminar, working from remote|
|Useful knowledge||Python, Machine Learning, Audio Processing|
|Work distribution||100% algorithm development|
|Med. Eng. designation||Advanced Context Recognition (ACR)|
|StudOn link||Please join|
|First Meeting||online-introduction-vorbesprechung-of-summer-term-2021-seminars, on 12th April 2021 at 16:15|
|Registration||Via StudOn, obligatory after introduction|
Up-to-date literature recommendations are provided during the lectures.
Final presentation and final report.