Difference between revisions of "2006:Audio Cover Song"

From MIREX Wiki
Line 3: Line 3:
  
 
==Task Description==
 
==Task Description==
Within the [[Audio Music Similarity and Retrieval]] database, there is imbedded 30 different "cover songs" each represented by 11 different
+
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 333 audio files (16bit, monophonic, 22.05khz). 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 X returned items for the presence of the other 10 versions of the "seed/query" file. Evaluation will be premised on classic precision and recall.
 +
 
 +
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.
 +
 
 +
==Comments==
 +
We at IMIRSEL expect that the overall scores for the Cover Song task will be quite low. This the first run at doing a Cover Song task and the baseline data collected from this year's experience will be used to create better Cover Song tasks for future MIREX iterations.
  
 
==Moderators==
 
==Moderators==

Revision as of 17:18, 18 July 2006

Overview

The Cover Song task is a new task for MIREX 2006. It is closely related to the Audio Music Similarity and Retrieval task. 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 333 audio files (16bit, monophonic, 22.05khz). 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 X returned items for the presence of the other 10 versions of the "seed/query" file. Evaluation will be premised on classic precision and recall.

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.

Comments

We at IMIRSEL expect that the overall scores for the Cover Song task will be quite low. This the first run at doing a Cover Song task and the baseline data collected from this year's experience will be used to create better Cover Song tasks for future MIREX iterations.

Moderators