Skip to Main content Skip to Navigation
Conference papers

Interactive Classification of Sound Objects for Polyphonic Electro-Acoustic Music Annotation

Abstract : In this paper, we present an interactive approach for the classification of sound objects in electro-acoustic music. For this purpose, we use relevance feedback combined with active-learning segment selection in an interactive loop. Validation and correction information given by the user is injected in the learning process at each iteration to achieve more accurate classification. Three active learning criteria are compared in the evaluation of a system classifying polyphonic pieces (with a varying degree of polyphony). The results show that the interactive approach achieves satisfying performance in a reasonable number of iterations.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-02713989
Contributor : Gaël Richard <>
Submitted on : Monday, June 1, 2020 - 7:20:48 PM
Last modification on : Tuesday, July 13, 2021 - 2:17:13 PM

Identifiers

  • HAL Id : hal-02713989, version 1

Citation

Sébastien Gulluni, Slim Essid, Olivier Buisson, Gael Richard. Interactive Classification of Sound Objects for Polyphonic Electro-Acoustic Music Annotation. AES Conference, 2011, Ilmenau, Germany. ⟨hal-02713989⟩

Share

Metrics

Record views

35