National Repository of Grey Literature 1 records found  Search took 0.01 seconds. 
Chord structure detection in music recordings
Kučera, Ondřej ; Miklánek, Štěpán (referee) ; Ištvánek, Matěj (advisor)
This thesis deals with music information retrieval, namely automatic chord recognition in audio recordings. The thesis defines the concepts of chord and chroma features and describes the methods of converting the signal from the time domain to the frequency domain. The thesis explores methods for automatic chord detection; the state-of-the-art methods are based on deep learning. The thesis includes a system implemented in Python that allows chord detection from audio recordings. Individual recordings and associated chord labels can be visualized. The system offers a choice of methods for chord recognition – a method based on chord templates, a method using deep chroma vectors, and a method based on a convolutional neural network. The results of the methods are evaluated on a multi-genre dataset compiled from freely available annotations and recordings.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.