Recognizing chords with EDS: part one

Authors:
Giordano Cabral;François Pachet;Jean-Pierre Briot
Affiliations:
Laboratoire d'Informatique de Paris 6, Paris, France;Sony Computer Science Lab, Paris, France;Laboratoire d'Informatique de Paris 6, Paris, France
Venue:
CMMR'05 Proceedings of the Third international conference on Computer Music Modeling and Retrieval
Year:
2005

Citing 2
Cited 2

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Machine Learning

Machine Learning

Analytical features: a knowledge-based approach to audio feature generation

EURASIP Journal on Audio, Speech, and Music Processing
Feature learning and deep architectures: new directions for music informatics

Journal of Intelligent Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.