2014:Query by Tapping - Revision history

Blair Kaneshiro at 18:31, 8 October 2014

2014-10-08T18:31:55Z

Blair Kaneshiro: /* Step 0: Indexing the MIDIs collection */

2014-08-28T05:22:08Z

‎Step 0: Indexing the MIDIs collection

Blair Kaneshiro: /* Step 2: Testing */

2014-08-28T05:20:37Z

‎Step 2: Testing

Blair Kaneshiro: /* Onset files format */

2014-08-28T02:12:31Z

‎Onset files format

Blair Kaneshiro: /* Step 2: Testing */

2014-08-28T02:11:41Z

‎Step 2: Testing

Blair Kaneshiro: /* Step 1: Training */

2014-08-28T02:09:53Z

‎Step 1: Training

Blair Kaneshiro: /* Step 0: Indexing the MIDIs collection */

2014-08-28T02:05:28Z

‎Step 0: Indexing the MIDIs collection

Blair Kaneshiro: /* Overview */

2014-07-17T22:11:23Z

‎Overview

Blair Kaneshiro: /* Discussions for 2014 */

2014-07-17T22:11:08Z

‎Discussions for 2014

Blair Kaneshiro: /* Potential Participants */

2014-07-15T00:25:49Z

‎Potential Participants

@@ Line 66: / Line 66: @@
 The command format should be like this:
-  qbtTraining <dbMidi_list> <query_file_list> [dir_workspace_root]
+  qbtTraining <dbMidi_list> <query_file_list_train> [dir_workspace_root]
-Where <code><dbMidi_list></code> is a list of the MIDI files in the database to match against (see Step 0), and <code><query_file_list></code> maps each query to its associated ground truth. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
+Where <code><dbMidi_list></code> is a list of the MIDI files in the database to match against (see Step 0), and <code><query_file_list_train></code> maps each query to its associated ground truth. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
 ==== Per-task input specification ====
-If the input query files are onset files (for subtask 1), then the format of <code><query_file_list></code> is like this (tab-separated):
+If the input query files are onset files (for subtask 1), then the format of <code><query_file_list_train></code> is like this (tab-separated):
   qbtQuery/query_00001.onset	00001.mid
@@ Line 111: / Line 111: @@
 The command format should be like this:
-  qbtTesting <query_file_list> <result_file> [dir_workspace_root]
+  qbtTesting <query_file_list_test> <result_file> [dir_workspace_root]
-Where <code><query_file_list></code> are input queries, and <code><result_file></code> is the filename where your script should store results. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
+Where <code><query_file_list_test></code> is a single-column text file of input queries (the <code>.onset</code> files only, not the <code>.mid</code> files), and <code><result_file></code> is the filename where your script should store results. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
 <code><result_file></code> gives ranked top-10 candidates for each query (note that ranking of the candidates is new for 2014). For instance <code><result_file></code> should have the following format for subtasks 1 and 3:

@@ Line 52: / Line 52: @@
   indexing <dbMidi.list> <dir_workspace_root>
-where <dbMidi.list> is the input list of database midi files named as uniq_key.mid. For example:
+where <code><dbMidi.list></code> is the input list of database midi files named as <code>uniq_key.mid</code>. For example:
   QBT/database/00001.mid

@@ Line 111: / Line 111: @@
 The command format should be like this:
-  qbtTesting <query_file_list> <resultFile> [dir_workspace_root]
+  qbtTesting <query_file_list> <result_file> [dir_workspace_root]
-Where <code><query_file_list></code> are input queries, and <code><resultFile></code> is the filename where your script should store results. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
+Where <code><query_file_list></code> are input queries, and <code><result_file></code> is the filename where your script should store results. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
-<code><resultFile></code> gives ranked top-10 candidates for each query (note that ranking of the candidates is new for 2014). For instance <code><resultFile></code> should have the following format for subtasks 1 and 3:
+<code><result_file></code> gives ranked top-10 candidates for each query (note that ranking of the candidates is new for 2014). For instance <code><result_file></code> should have the following format for subtasks 1 and 3:
   qbtQuery/query_00001.onset: 00025 01003 02200 ...

@@ Line 104: / Line 104: @@
 .0 479.922 720.069 976.071 1215.694
-For subtask 3, the additional dimension (position/pitch/contour) is provided in a file with the same name, but with extension <code>.y_onset</code>. Similarly to an .onset file, <code>.y_onset</code> files are space-separated text files, the same length as the corresponding <code>.onset</code> file, that lists the absolute vertical position of each tap on the touchscreen. Example (corresponding to above):
+For subtask 3, the additional dimension (position/pitch/contour) is provided in a file with the same name, but with extension <code>.y_onset</code>. Similarly to an <code>.onset</code> file, <code>.y_onset</code> files are space-separated text files, the same length as the corresponding <code>.onset</code> file, that lists the absolute vertical position of each tap on the touchscreen. Example (corresponding to above):
 .000000 293.500000 305.500000 302.000000 239.000000

@@ Line 113: / Line 113: @@
   qbtTesting <query_file_list> <resultFile> [dir_workspace_root]
-Where <query_file_list> are input queries, and <resultFile> is the filename where your script should store results. You can use [dir_workspace_root] to store any temporary indexing/database structures. (You can omit [dir_workspace_root] if you do not need it at all.)
+Where <code><query_file_list></code> are input queries, and <code><resultFile></code> is the filename where your script should store results. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
-<resultFile> gives ranked top-10 candidates for each query (note that ranking of the candidates is new for 2014). For instance <resultFile> should have the following format for subtasks 1 and 3:
+<code><resultFile></code> gives ranked top-10 candidates for each query (note that ranking of the candidates is new for 2014). For instance <code><resultFile></code> should have the following format for subtasks 1 and 3:
   qbtQuery/query_00001.onset: 00025 01003 02200 ...

@@ Line 68: / Line 68: @@
   qbtTraining <dbMidi_list> <query_file_list> [dir_workspace_root]
-Where <dbMidi_list> is a list of the MIDI files in the database to match against (see Step 0), and <query_file_list> maps each query to its associated ground truth. You can use [dir_workspace_root] to store any temporary indexing/database structures. (You can omit [dir_workspace_root] if you do not need it at all.)
+Where <code><dbMidi_list></code> is a list of the MIDI files in the database to match against (see Step 0), and <code><query_file_list></code> maps each query to its associated ground truth. You can use <code>[dir_workspace_root]</code> to store any temporary indexing/database structures. (You can omit <code>[dir_workspace_root]</code> if you do not need it at all.)
 ==== Per-task input specification ====
-If the input query files are onset files (for subtask 1), then the format of <query_file_list> is like this (tab-separated):
+If the input query files are onset files (for subtask 1), then the format of <code><query_file_list></code> is like this (tab-separated):
   qbtQuery/query_00001.onset	00001.mid
@@ Line 80: / Line 80: @@
 See details of [[#Onset files format|Onset files format]]
-If the input query files are wave files (for subtask 2), the the format of <query_file_list> is like this (tab-separated):
+If the input query files are wave files (for subtask 2), the the format of <code><query_file_list></code> is like this (tab-separated):
   qbtQuery/query_00001.wav	00001.mid
@@ Line 87: / Line 87: @@
   ...
-If the input query files are .onset and .y_onset files (for subtask 3), then the format of <query_file_list> is like this (tab-separated):
+If the input query files are <code>.onset</code> and <code>.y_onset</code> files (for subtask 3), then the format of <code><query_file_list></code> is like this (tab-separated):
   qbtQuery/query_00001.onset	qbtQuery/query_00001.y_onset	00001.mid
@@ Line 98: / Line 98: @@
 ===== Onset files format  =====
-To preserve compatibility with the original task, the QBT-E query files share the same .onset file extension as previous symbolic input query datasets.
+To preserve compatibility with the original task, the QBT-E query files share the same <code>.onset</code> file extension as previous symbolic input query datasets.
-An .onset file is a space-separated text file of elapsed onset times (in milliseconds) from the first onset, which is always 0.0. Example of 5 onsets:
+An <code>.onset</code> file is a space-separated text file of elapsed onset times (in milliseconds) from the first onset, which is always 0.0. Example of 5 onsets:
 .0 479.922 720.069 976.071 1215.694
-For subtask 3, the additional dimension (position/pitch/contour) is provided in a file with the same name, but with extension <code>.y_onset</code>. Similarly to an .onset file, <code>.y_onset</code> files are space-separated text files, the same length as the corresponding .onset file, that lists the absolute vertical position of each tap on the touchscreen. Example (corresponding to above):
+For subtask 3, the additional dimension (position/pitch/contour) is provided in a file with the same name, but with extension <code>.y_onset</code>. Similarly to an .onset file, <code>.y_onset</code> files are space-separated text files, the same length as the corresponding <code>.onset</code> file, that lists the absolute vertical position of each tap on the touchscreen. Example (corresponding to above):
 .000000 293.500000 305.500000 302.000000 239.000000

@@ Line 60: / Line 60: @@
   ...
-Output indexed files are placed into <dir_workspace_root>.
+Output indexed files are placed into <code><dir_workspace_root></code>.
 === Step 1: Training ===

← Older revision		Revision as of 22:11, 17 July 2014
Line 1:		Line 1:
	== Overview ==		== Overview ==
−	~~The text of this section is copied from the 2013 page. Please add your comments and discussions for 2014.~~
−
	The main purpose of QBT (Query by Tapping) is to evaluate MIR system in retrieving ground-truth MIDI files by tapping the onset of music notes to the microphone. This task provides query files in wave format as well as the corresponding human-label onset time in symbolic format. For this year's QBT task, we have three corpora for evaluation:		The main purpose of QBT (Query by Tapping) is to evaluate MIR system in retrieving ground-truth MIDI files by tapping the onset of music notes to the microphone. This task provides query files in wave format as well as the corresponding human-label onset time in symbolic format. For this year's QBT task, we have three corpora for evaluation:

@@ Line 14: / Line 14: @@
 == Discussions for 2014 ==
 CCRMA is very excited to be hosting the QBT task this year!
 Any questions or suggestions can be added directly here, or you can send us an email, qbt | at | ccrma dot stanford dot edu
 == Task description ==

@@ Line 126: / Line 126: @@
 == Potential Participants ==
-Jorge Herrera, Hyung-Suk Kim, and Blair Kaneshiro, CCRMA, jorgeh at ccrma dot stanford dot edu
+Jorge Herrera, Hyung-Suk Kim, and Blair Kaneshiro, CCRMA, qbt at ccrma dot stanford dot edu
 == References ==