Skip to Main content Skip to Navigation
Conference papers

A roadmap towards versatile MIR

Emmanuel Vincent 1 Stanislaw Raczynski 2 Nobutaka Ono 2 Shigeki Sagayama 2
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Most MIR systems are specifically designed for one application and one cultural context and suffer from the semantic gap between the data and the application. Advances in the theory of Bayesian language and information processing enable the vision of a versatile, meaningful and accurate MIR system integrating all levels of information. We propose a roadmap to collectively achieve this vision.
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download
Contributor : Emmanuel Vincent Connect in order to contact the contributor
Submitted on : Tuesday, December 7, 2010 - 11:05:57 AM
Last modification on : Wednesday, June 16, 2021 - 3:34:55 AM
Long-term archiving on: : Tuesday, March 8, 2011 - 3:04:46 AM


Publisher files allowed on an open archive


  • HAL Id : inria-00544047, version 1


Emmanuel Vincent, Stanislaw Raczynski, Nobutaka Ono, Shigeki Sagayama. A roadmap towards versatile MIR. 2010 Int. Society for Music Information Retrieval Conf. (ISMIR), Aug 2010, Utrecht, Netherlands. pp.662--664. ⟨inria-00544047⟩



Record views


Files downloads