Difference between revisions of "2007:Audio Cover Song Identification"

From MIREX Wiki
(Task Description)
Line 5: Line 5:
 
Within the [[Audio Music Similarity and Retrieval]] database, there are embedded 30 different "cover songs" each represented by 11 different "versions" for a total of 330 audio files (16bit, monophonic, 22.05khz, wav). The "cover songs" represent a variety of genres (e.g., classical, jazz, gospel, rock, folk-rock, etc.) and the variations span a variety of styles and orchestrations.  
 
Within the [[Audio Music Similarity and Retrieval]] database, there are embedded 30 different "cover songs" each represented by 11 different "versions" for a total of 330 audio files (16bit, monophonic, 22.05khz, wav). The "cover songs" represent a variety of genres (e.g., classical, jazz, gospel, rock, folk-rock, etc.) and the variations span a variety of styles and orchestrations.  
  
Using each of these cover song files in turn as as the "seed/query" file, we will examine the top 10 returned items for the presence of the other 10 versions of the "seed/query" file. Evaluation will be premised on classic precision and recall.  
+
Using each of these cover song files in turn as as the "seed/query" file, we will examine the top 10 returned items for the presence of the other 10 versions of the "seed/query" file.
  
 
Participants in the [[Audio Music Similarity and Retrieval]] task really need not do anything extra as the matrices returned will contain all the necessary information for us to automatically conduct the evaluations. We do encourage, however, the participation of those systems that might be especially designed to detect "cover song" variants.
 
Participants in the [[Audio Music Similarity and Retrieval]] task really need not do anything extra as the matrices returned will contain all the necessary information for us to automatically conduct the evaluations. We do encourage, however, the participation of those systems that might be especially designed to detect "cover song" variants.
 +
 +
==Evaluation==
 +
 +
We could employ the same measures used in [[2006:Audio Cover Song]].
 +
 +
== Comments ==
 +
 +
Evaluation measures: Perhaps the MRR of the 1st correctly classified instance could be changed to the MRR of the whole 10 answers...
  
 
==Moderators==
 
==Moderators==
Line 14: Line 22:
 
* anyone else?
 
* anyone else?
  
== Participants ==
+
==Potential Participants==
  
 
+
* Joan Serrà (jserra at iua dot upf dot edu) and Emilia Gómez (egomez at iua dot upf dot edu)
== Comments ==
 

Revision as of 04:13, 13 June 2007

Overview

The Cover Song task was a new task for MIREX 2006. It is closely related to the Audio Music Similarity and Retrieval task as the cover songs to be found will be embedded in the Audio Music Similarity and Retrieval test collection. Hence, the setup and running of the algorithms will be the same as that of the Audio Music Similarity and Retrieval so please refer to the Audio Music Similarity and Retrieval for more details.

Task Description

Within the Audio Music Similarity and Retrieval database, there are embedded 30 different "cover songs" each represented by 11 different "versions" for a total of 330 audio files (16bit, monophonic, 22.05khz, wav). The "cover songs" represent a variety of genres (e.g., classical, jazz, gospel, rock, folk-rock, etc.) and the variations span a variety of styles and orchestrations.

Using each of these cover song files in turn as as the "seed/query" file, we will examine the top 10 returned items for the presence of the other 10 versions of the "seed/query" file.

Participants in the Audio Music Similarity and Retrieval task really need not do anything extra as the matrices returned will contain all the necessary information for us to automatically conduct the evaluations. We do encourage, however, the participation of those systems that might be especially designed to detect "cover song" variants.

Evaluation

We could employ the same measures used in 2006:Audio Cover Song.

Comments

Evaluation measures: Perhaps the MRR of the 1st correctly classified instance could be changed to the MRR of the whole 10 answers...

Moderators

Potential Participants

  • Joan Serr├á (jserra at iua dot upf dot edu) and Emilia G├│mez (egomez at iua dot upf dot edu)