From Improved Auto-taggers to Improved Music Similarity Measures.

Klaus Seyerlehner; Reinhard Sonnleitner; Markus Schedl; David Hauger; B. Ionescu

From Improved Auto-taggers to Improved Music Similarity Measures.

Klaus Seyerlehner
, Reinhard Sonnleitner
, Markus Schedl
, David Hauger
, B. Ionescu

Institut für Computational Perception

Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung

Abstract

This paper focuses on the relation between automatic tag prediction and music similarity. Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors. We present classification experiments that verify this claim. Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.

Originalsprache	Englisch
Titel	Proceedings of the 10th International Workshop on Adaptive Multimedia Retrieval (AMR 2012)
Seitenumfang	10
Publikationsstatus	Veröffentlicht - Okt. 2012

Wissenschaftszweige

102 Informatik
102001 Artificial Intelligence
102003 Bildverarbeitung

JKU-Schwerpunkte

Computation in Informatics and Mathematics
TNF Allgemein

Dieses zitieren

@inproceedings{b92709a3dd764aa09dc156e9c2b35505,

title = "From Improved Auto-taggers to Improved Music Similarity Measures.",

abstract = "This paper focuses on the relation between automatic tag prediction and music similarity. Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors. We present classification experiments that verify this claim. Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.",

author = "Klaus Seyerlehner and Reinhard Sonnleitner and Markus Schedl and David Hauger and B. Ionescu",

year = "2012",

month = oct,

language = "English",

booktitle = "Proceedings of the 10th International Workshop on Adaptive Multimedia Retrieval (AMR 2012)",

}

TY - GEN

T1 - From Improved Auto-taggers to Improved Music Similarity Measures.

AU - Seyerlehner, Klaus

AU - Sonnleitner, Reinhard

AU - Schedl, Markus

AU - Hauger, David

AU - Ionescu, B.

PY - 2012/10

Y1 - 2012/10

N2 - This paper focuses on the relation between automatic tag prediction and music similarity. Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors. We present classification experiments that verify this claim. Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.

AB - This paper focuses on the relation between automatic tag prediction and music similarity. Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors. We present classification experiments that verify this claim. Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.

M3 - Conference proceedings

BT - Proceedings of the 10th International Workshop on Adaptive Multimedia Retrieval (AMR 2012)

ER -