Giordano Cabral, François Pachet, and Jean-Pierre Briot. Recognizing chords with EDS: Part one. In R. Kronland-Martinet et al., editor, Proceedings of the 6th Computer Music Modeling and Retrieval (CMMR'2005), Lecture Notes in Computer Science (vol. 3902), pages 185-195, Pisa, Italy, September 2005 Springer.

Sony CSL authors: François Pachet


This paper presents a comparison between traditional and automatic approaches for the extraction of an audio descriptor to recognize chord into classes. The traditional approach requires signal processing (SP) skills, constraining it to be used only by expert users. The Extractor Discovery System (EDS) [1] is a recent approach, which can also be useful for non expert users, since it intends to discover such descriptors automatically. This work compares the results from a classic approach for chord recognition, namely the use of KNN-learners over Pitch Class Profiles (PCP), with the results from EDS when operated by a non SP expert.

Keywords: feature, generation


[PDF] Adobe Acrobat PDF file

BibTeX entry

@INPROCEEDINGS { cabral:05b, ADDRESS="Pisa, Italy", AUTHOR="Giordano Cabral, François Pachet, and Jean-Pierre Briot.", BOOKTITLE="Proceedings of the 6th Computer Music Modeling and Retrieval (CMMR\'2005)", EDITOR="R. Kronland-Martinet et al.", MONTH="September", PAGES="185-195", PUBLISHER="Springer", SERIES="Lecture Notes in Computer Science", TITLE="Recognizing chords with EDS: Part one", VOLUME="3902", YEAR="2005", }