2008:Audio Cover Song Identification - Revision history

Kahyun Choi: /* Evaluation */

2011-12-20T04:14:32Z

‎Evaluation

Kahyun Choi: /* 2008 AUDIO COVER SONG IDENTIFICATION TASK OVERVIEW */

2011-12-20T04:14:00Z

‎2008 AUDIO COVER SONG IDENTIFICATION TASK OVERVIEW

IMIRSELBot: Robot: Automated text replacement (-\[\[([A-Z][^:]+)\]\] +2008:\1)

2010-05-13T18:23:01Z

Robot: Automated text replacement (-\[\[([A-Z][^:]+)\]\] +2008:\1)

CameronJones: /* Command Line Calling Format */

2008-08-18T21:56:17Z

‎Command Line Calling Format

CameronJones: /* Command Line Calling Format */

2008-08-18T21:55:50Z

‎Command Line Calling Format

CameronJones: /* Command Line Calling Format */

2008-08-18T21:53:03Z

‎Command Line Calling Format

CameronJones: /* Input Files */

2008-08-18T21:51:51Z

‎Input Files

CameronJones: /* Command Line Calling Format */

2008-08-18T21:48:40Z

‎Command Line Calling Format

CameronJones: /* Calling Procedure */

2008-08-18T21:48:15Z

‎Calling Procedure

CameronJones: /* Calling Procedure */

2008-08-18T21:45:11Z

‎Calling Procedure

← Older revision		Revision as of 04:14, 20 December 2011
Line 89:		Line 89:


−	Any way to get evaluation databases from 2006 and 2007? --~~[[User:znv\|~~Gene Linetsky]]	+	Any way to get evaluation databases from 2006 and 2007? -- Gene Linetsky

	For copyright reasons IMIRSEL does not distribute its evaluation databases. Further, keeping the evaluation dataset (somewhat) closed anables it to be used yea on year, with less chance of any system being particularly over-fitted to it and thereby achieving inflated performance estimates.		For copyright reasons IMIRSEL does not distribute its evaluation databases. Further, keeping the evaluation dataset (somewhat) closed anables it to be used yea on year, with less chance of any system being particularly over-fitted to it and thereby achieving inflated performance estimates.

@@ Line 1: / Line 1: @@
 =2008 AUDIO COVER SONG IDENTIFICATION TASK OVERVIEW=
-The Audio Cover Song task was a new task for MIREX 2006. It was closely related to the [[2008:Audio Music Similarity and Retrieval]] (AMS) task as the cover songs were embedded in the Audio Music Similarity and Retrieval test collection. However, AMS has change its input format this year so Audio Cover Song and AMS will not be interlinked tasks this year.
+The Audio Cover Song task was a new task for MIREX 2006. It was closely related to the [[2007:Audio Music Similarity and Retrieval]] (AMS) task as the cover songs were embedded in the Audio Music Similarity and Retrieval test collection. However, AMS has change its input format this year so Audio Cover Song and AMS will not be interlinked tasks this year.
 ==Task Description==

@@ Line 1: / Line 1: @@
 =2008 AUDIO COVER SONG IDENTIFICATION TASK OVERVIEW=
-The Audio Cover Song task was a new task for MIREX 2006. It was closely related to the [[Audio Music Similarity and Retrieval]] (AMS) task as the cover songs were embedded in the Audio Music Similarity and Retrieval test collection. However, AMS has change its input format this year so Audio Cover Song and AMS will not be interlinked tasks this year.
+The Audio Cover Song task was a new task for MIREX 2006. It was closely related to the [[2008:Audio Music Similarity and Retrieval]] (AMS) task as the cover songs were embedded in the Audio Music Similarity and Retrieval test collection. However, AMS has change its input format this year so Audio Cover Song and AMS will not be interlinked tasks this year.
 ==Task Description==

@@ Line 11: / Line 11: @@
   $ /path/to/submission <collection_list_file> <query_list_file> <working_directory> <output_file>
-      <collection_list_file>: Text file containing 1000 full path file names for the
+      '''<collection_list_file>''': Text file containing 1000 full path file names for the
 audio files in the collection (including the 330
                               query documents).
                               '''Example: /path/to/coversong/collection.txt'''
-      <query_list_file>     : Text file containing the 330 full path file names for the
+      '''<query_list_file>'''     : Text file containing the 330 full path file names for the
 query documents.
                               '''Example: /path/to/coversong/queries.txt'''
-      <working_directory>   : Full path to a temporary directory where submission will
+      '''<working_directory>'''   : Full path to a temporary directory where submission will
                               have write access for caching features or calculations.
                               '''Example: /tmp/submission_id/'''
-      <output_file>         : Full path to file where submission should output the similarity
+      '''<output_file>'''         : Full path to file where submission should output the similarity
                               matrix (1000 header rows + 330 x 1000 data matrix).
                               '''Example: /path/to/coversong/results/submission_id.txt'''

@@ Line 14: / Line 14: @@
 audio files in the collection (including the 330
                               query documents).
-                              Example: /path/to/coversong/collection.txt
+                              '''Example: /path/to/coversong/collection.txt'''
       <query_list_file>     : Text file containing the 330 full path file names for the
 query documents.
-                              Example: /path/to/coversong/queries.txt
+                              '''Example: /path/to/coversong/queries.txt'''
       <working_directory>   : Full path to a temporary directory where submission will
                               have write access for caching features or calculations.
-                              Example: /tmp/submission_id/
+                              '''Example: /tmp/submission_id/'''
       <output_file>         : Full path to file where submission should output the similarity
                               matrix (1000 header rows + 330 x 1000 data matrix).
-                              Example: /path/to/coversong/results/submission_id.txt
+                              '''Example: /path/to/coversong/results/submission_id.txt'''
 === Input Files ===

@@ Line 23: / Line 23: @@
 === Input Files ===
-The input lists file format will be of the form:
+The collection lists file format will be of the form:
-<pre>
+ /path/to/audio/file/000.wav\n
-path/to/audio/file/000001.wav
+ /path/to/audio/file/001.wav\n
-path/to/audio/file/000002.wav
+ /path/to/audio/file/002.wav\n
-path/to/audio/file/000003.wav
+ ... * 996 rows omitted * ...
-...
+ /path/to/audio/file/999.wav\n
-Two input files will be provide:
+The query lists file format will be of the form:
 === Output File ===

@@ Line 8: / Line 8: @@
-=== Calling Procedure ===
+=== Command Line Calling Format ===
-  $ binary <collection_list_file> <query_list_file> <working_directory> <output_file>
+  $ /path/to/submission <collection_list_file> <query_list_file> <working_directory> <output_file>
       <collection_list_file>: Text file containing 1000 full path file names for the
 audio files in the collection (including the 330