No full text
Paper published in a book (Scientific congresses and symposiums)
Efficient database pruning for large-scale cover song recognition
Osmalsky, Julien; Pierard, Sébastien; Van Droogenbroeck, Marc et al.
2013In International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Peer reviewed
 

Files


Full Text
No document available.
Annexes
Osmalskyj2013Efficient.pdf
Publisher postprint (282.47 kB)
Efficient database pruning for large-scale cover song recognition
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Speech; Recognition; Million Song Dataset; Music Information Retrieval; Chromas; Rejectors; Cover Songs
Abstract :
[en] This paper focuses on cover song recognition over a large dataset, potentially containing millions of songs. At this time, the problem of cover song recognition is still challenging and only few methods have been proposed on large scale databases. We present an efficient method for quickly extracting a small subset from a large database in which a correspondence to an audio query should be found. We make use of fast rejectors based on independent audio features. Our method mixes independent rejectors together to build composite ones. We evaluate our system with the Million Song Dataset and we present composite rejectors offering a good trade-off between the percentage of pruning and the percentage of loss.
Research center :
Intelsig
Disciplines :
Electrical & electronics engineering
Author, co-author :
Osmalsky, Julien ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Techniques du son et de l'image
Pierard, Sébastien ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore)
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Embrechts, Jean-Jacques ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Techniques du son et de l'image
Language :
English
Title :
Efficient database pruning for large-scale cover song recognition
Publication date :
May 2013
Event name :
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Event organizer :
IEEE
Event place :
Vancouver, United States
Event date :
from 26-05-2013 to 31-05-2013
Audience :
International
Main work title :
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Publisher :
IEEE
Peer reviewed :
Peer reviewed
Available on ORBi :
since 06 March 2013

Statistics


Number of views
234 (64 by ULiège)
Number of downloads
318 (27 by ULiège)

Bibliography


Similar publications



Contact ORBi