SIMAC: Semantic Interaction with Music Audio Contents

Perfecto Herrera; Juan Bello; Gerhard Widmer; Mark Sandler; Xavier Serra; Fabio Vignoli; Elias Pampalk; Pedro Cano; Steffen Pauws; Oskar Celma

SIMAC: Semantic Interaction with Music Audio Contents

Perfecto Herrera
, Juan Bello
, Gerhard Widmer
, Mark Sandler
, Xavier Serra
, Fabio Vignoli
, Elias Pampalk
, Pedro Cano
, Steffen Pauws
, Oskar Celma

Institute of Computational Perception

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

The SIMAC project addresses the study and development of innovative components for a music information retrieval system. The key feature is the usage and exploitation of semantic descriptors of musical content that are automatically extracted from music audio files. These descriptors are generated in two ways: as derivations and combinations of lower-level descriptors and as generalizations induced from manually annotated databases by the intensive application of machine learning. The project aims also towards the empowering (i.e. adding value, improving effectiveness) of music consumption behaviours, especially of those that are guided by the concept of similarity.

Original language	English
Title of host publication	In Proceedings of the 2nd European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies (EWIMT 2005), Pisa, Italy
Number of pages	8
Publication status	Published - 2005

Fields of science

102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems
202002 Audiovisual media

Cite this

@inproceedings{b06a9cc892b14738954999506f22188f,

title = "SIMAC: Semantic Interaction with Music Audio Contents",

abstract = "The SIMAC project addresses the study and development of innovative components for a music information retrieval system. The key feature is the usage and exploitation of semantic descriptors of musical content that are automatically extracted from music audio files. These descriptors are generated in two ways: as derivations and combinations of lower-level descriptors and as generalizations induced from manually annotated databases by the intensive application of machine learning. The project aims also towards the empowering (i.e. adding value, improving effectiveness) of music consumption behaviours, especially of those that are guided by the concept of similarity.",

author = "Perfecto Herrera and Juan Bello and Gerhard Widmer and Mark Sandler and Xavier Serra and Fabio Vignoli and Elias Pampalk and Pedro Cano and Steffen Pauws and Oskar Celma",

year = "2005",

language = "English",

booktitle = "In Proceedings of the 2nd European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies (EWIMT 2005), Pisa, Italy",

}

TY - GEN

T1 - SIMAC: Semantic Interaction with Music Audio Contents

AU - Herrera, Perfecto

AU - Bello, Juan

AU - Widmer, Gerhard

AU - Sandler, Mark

AU - Serra, Xavier

AU - Vignoli, Fabio

AU - Pampalk, Elias

AU - Cano, Pedro

AU - Pauws, Steffen

AU - Celma, Oskar

PY - 2005

Y1 - 2005

N2 - The SIMAC project addresses the study and development of innovative components for a music information retrieval system. The key feature is the usage and exploitation of semantic descriptors of musical content that are automatically extracted from music audio files. These descriptors are generated in two ways: as derivations and combinations of lower-level descriptors and as generalizations induced from manually annotated databases by the intensive application of machine learning. The project aims also towards the empowering (i.e. adding value, improving effectiveness) of music consumption behaviours, especially of those that are guided by the concept of similarity.

AB - The SIMAC project addresses the study and development of innovative components for a music information retrieval system. The key feature is the usage and exploitation of semantic descriptors of musical content that are automatically extracted from music audio files. These descriptors are generated in two ways: as derivations and combinations of lower-level descriptors and as generalizations induced from manually annotated databases by the intensive application of machine learning. The project aims also towards the empowering (i.e. adding value, improving effectiveness) of music consumption behaviours, especially of those that are guided by the concept of similarity.

M3 - Conference proceedings

BT - In Proceedings of the 2nd European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies (EWIMT 2005), Pisa, Italy

ER -