Evolutionary algorithms and automatic transcription of music

Reis, Gustavo; Fernandéz, Francisco; Ferreira, Aníbal

http://hdl.handle.net/10400.8/15343

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
2330784.2330857.pdf		817.62 KB	Adobe PDF	Download

Send Feedback

Authors

Reis, Gustavo

Fernandéz, Francisco

Ferreira, Aníbal

Abstract(s)

The main problem behind Automatic Transcription (Multiple Fundamental Frequency - F0 - Estimation) relies on its complexity. Harmonic collision and partial overlapping create a frequency lattice that is almost impossible to deconstruct. Although traditional approaches to this problem of rely mainly in Digital Signal Processing (DSP) techniques, evolutionary algorithms have been applied recently to this problem and achieved competitive results. We describe all evolutionary approaches to the problem of automatic music transcription and how some were improved so they could achieve competitive results. Finally, we show how the best evolutionary approach performs on piano transcription, when compared with the state-of-the-art.

Keywords

Automatic Music Transcription Pitch Estimation Multiple F0 Estimation Genetic Algorithms

URI

http://hdl.handle.net/10400.8/15343

Citation

Gustavo Reis, Francisco Fernandéz, and Aníbal Ferreira. 2012. Evolutionary algorithms and automatic transcription of music. In Proceedings of the 14th annual conference companion on Genetic and evolutionary computation (GECCO '12). Association for Computing Machinery, New York, NY, USA, 477–484. https://doi.org/10.1145/2330784.2330857