2014:Audio Fingerprinting - Revision history

Chung-Che Wang: /* Time and hardware limits */

2014-09-23T12:42:21Z

‎Time and hardware limits

Chung-Che Wang: /* Time and hardware limits */

2014-09-23T12:40:39Z

‎Time and hardware limits

Chung-Che Wang: /* Submission Format */

2014-09-03T03:28:03Z

‎Submission Format

Chung-Che Wang: /* References */

2014-08-30T09:12:26Z

‎References

Chung-Che Wang at 09:12, 30 August 2014

2014-08-30T09:12:14Z

Chung-Che Wang at 09:06, 30 August 2014

2014-08-30T09:06:10Z

Jyh-Shing Roger Jang: /* Time and hardware limits */

2014-08-12T15:08:55Z

‎Time and hardware limits

Jyh-Shing Roger Jang: /* Time and hardware limits */

2014-08-12T14:56:06Z

‎Time and hardware limits

Jyh-Shing Roger Jang: /* Submission Format */

2014-08-12T14:43:35Z

‎Submission Format

Jyh-Shing Roger Jang: /* Query set */

2014-08-12T14:39:47Z

‎Query set

@@ Line 66: / Line 66: @@
 | builder || 24 hours || 50KB for 1 minute of music. (For a database of 10000 songs, the total storage for database should be around 50*10000*4/1000000 = 2GB.)
 |-
-| matcher || 12 hours || None
+| matcher || 24 hours || None
 |}
 Submissions that exceed these limitations may not receive a result.

@@ Line 64: / Line 64: @@
 ! Steps !! Time limit !! Storage limit
 |-
-| builder || 1/50 of real time (For instance, if a music clip has a duration of 4 minutes, it should take 4.8 sec to construct the database in average. For a database of 10000 songs, the total time should around 10000*4/60/50 = 13.33 hours.) || 50KB for 1 minute of music. (For a database of 10000 songs, the total storage for database should be around 50*10000*4/1000000 = 2GB.)
+| builder || 24 hours || 50KB for 1 minute of music. (For a database of 10000 songs, the total storage for database should be around 50*10000*4/1000000 = 2GB.)
 |-
-| matcher || 5 secs for each query of around 10 seconds (Thus for 5692 queries of around 10 seconds, the total query time should be around 5*5692/3600 = 7.91 hours.) || None
+| matcher || 12 hours || None
 |}
 Submissions that exceed these limitations may not receive a result.

@@ Line 28: / Line 28: @@
 Command format:
   builder %fileList4db% %dir4db%
-where %fileList4db% is a file containing the input list of database audio files, with name convention as uniqueKey.wav. For example:
+where %fileList4db% is a file containing the input list of database audio files, with name convention as uniqueKey.mp3. For example:
   ./AFP/database/000001.mp3
   ./AFP/database/000002.mp3

← Older revision		Revision as of 09:12, 30 August 2014
Line 80:		Line 80:

	[1] Bob L. Sturm, ``The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval,'' J. New Music Research, vol. 43, no. 2, pp. 147–172, 2014.		[1] Bob L. Sturm, ``The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval,'' J. New Music Research, vol. 43, no. 2, pp. 147–172, 2014.
		+
	[2] Faults in the GTZAN Music Genre Dataset, available at http://imi.aau.dk/~bst/research/GTZANtable2/ , 2014.		[2] Faults in the GTZAN Music Genre Dataset, available at http://imi.aau.dk/~bst/research/GTZANtable2/ , 2014.

@@ Line 6: / Line 6: @@
 ,000 songs (*.mp3) in the database, in which there is exact one song corresponding to each query. (That is, there is no out-of-vocabulary query in the query set.) 965 of the files are from GTZAN data set, all the others are mainly English and Chinese pop songs. This data set is hidden and not available for download. (Note that there are possibly different numbers of channels (mono and stereo), sampling rates, and bit resolutions for these files.)
-The GTZAN data set were purified according to [1]. Exact repetitions were considered by the following principles:
+The GTZAN data set were purified according to [1][2]. Exact repetitions were considered by the following principles:
 * If none of the songs in a repetition set has corresponding queries, then nothing is removed from the database.
 * If one of the songs in a repetition set has corresponding queries, then all the other songs (which have no corresponding queries) were removed from the database.
@@ Line 80: / Line 80: @@
 [1] Bob L. Sturm, ``The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval,'' J. New Music Research, vol. 43, no. 2, pp. 147–172, 2014.

@@ Line 4: / Line 4: @@
 == Data ==
 === Database ===
-* 10,000 songs (*.mp3) in the database, in which there is exact one song corresponding to each query. (That is, there is no out-of-vocabulary query in the query set.) 1,000 of the files are from GTZAN data set, all the others are mainly English and Chinese pop songs. This data set is hidden and not available for download. (Note that there are possibly different numbers of channels (mono and stereo), sampling rates, and bit resolutions for these files.)
+,000 songs (*.mp3) in the database, in which there is exact one song corresponding to each query. (That is, there is no out-of-vocabulary query in the query set.) 965 of the files are from GTZAN data set, all the others are mainly English and Chinese pop songs. This data set is hidden and not available for download. (Note that there are possibly different numbers of channels (mono and stereo), sampling rates, and bit resolutions for these files.)
 === Query set ===
@@ Line 70: / Line 75: @@
 name / email
-= Bibliography =
+== Bibliography ==

@@ Line 59: / Line 59: @@
 ! Steps !! Time limit !! Storage limit
 |-
-| builder || 1/100 of real time (For instance, if a music clip has a duration of 4 minutes, it should take 2.4 sec to construct the database in average. For a database of 10000 songs, the total time should around 10000*4/60/100 = 6.7 hours.) || 50KB for 1 minute of music. (For a database of 10000 songs, the total storage for database should be around 50*10000*4/1000000 = 2GB.)
+| builder || 1/50 of real time (For instance, if a music clip has a duration of 4 minutes, it should take 4.8 sec to construct the database in average. For a database of 10000 songs, the total time should around 10000*4/60/50 = 13.33 hours.) || 50KB for 1 minute of music. (For a database of 10000 songs, the total storage for database should be around 50*10000*4/1000000 = 2GB.)
 |-
 | matcher || 2 secs for each query of around 10 seconds (Thus for 5692 queries of around 10 seconds, the total query time should be around 2*5692/3600 = 3.2 hours.) || None

@@ Line 24: / Line 24: @@
   builder %fileList4db% %dir4db%
 where %fileList4db% is a file containing the input list of database audio files, with name convention as uniqueKey.wav. For example:
-  ./AFP/database/00001.mp3
+  ./AFP/database/000001.mp3
-  ./AFP/database/00002.mp3
+  ./AFP/database/000002.mp3
-  ./AFP/database/00003.mp3
+  ./AFP/database/000003.mp3
-  ./AFP/database/00004.mp3
+  ./AFP/database/000004.mp3
   ...
-The output file(s), which containing all the information of the database to be used for audio fingerprinting, should be placed placed into the directory %dir4db%. The size of the database file(s) is restricted to a certain amount, as explained next.
+The output file(s), which containing all the information of the database to be used for audio fingerprinting, should be placed placed into the directory %dir4db%. The total size of the database file(s) is restricted to a certain amount, as explained next.
 . Matcher
@@ Line 37: / Line 37: @@
   matcher %fileList4query% %dir4db% %resultFile%
 where %fileList4query% is a file containing the list of query clips. For example:
-  ./AFP/query/q0001.wav
+  ./AFP/query/q000001.wav
-  ./AFP/query/q0002.wav
+  ./AFP/query/q000002.wav
-  ./AFP/query/q0003.wav
+  ./AFP/query/q000003.wav
-  ./AFP/query/q0004.wav
+  ./AFP/query/q000004.wav
   ...
@@ Line 49: / Line 49: @@
 where these two fields are separated by a tab. Here is a more specific example:
-  ./AFP/query/q0001.wav	./AFP/database/00004.mp3
+  ./AFP/query/q000001.wav	./AFP/database/0000004.mp3
-  ./AFP/query/q0002.wav	./AFP/database/00054.mp3
+  ./AFP/query/q000002.wav	./AFP/database/0000054.mp3
-  ./AFP/query/q0003.wav	./AFP/database/01002.mp3
+  ./AFP/query/q000003.wav	./AFP/database/0001002.mp3
   ..

@@ Line 11: / Line 11: @@
 * 1062 clips of wav format: These recordings are noisy versions of George's music genre dataset. You can download the query set via [http://mirlab.org/dataSet/public/queryPublic_George.rar this link]
-All the query set is mono recordings of 8-12 sec, with 44.1 KHz sampling rate and 16-bit resolution. The set was obtained via different brands of smartphone, at various locations with various kinds of environmental noise.
+All the query set is mono recordings of 8-12 sec, with 44.1 KHz sampling rate and 16-bit resolution. The set was obtained via different brands of smartphones, at various locations with various kinds of environmental noise.
 == Evaluation Procedures ==