2007:Audio Chord Detection - Revision history

Mikejdi: /* Potential Participants */

2007-12-06T17:37:12Z

‎Potential Participants

Mikejdi: /* Potential Participants */

2007-10-05T17:27:43Z

‎Potential Participants

Papadopo: /* Potential Participants */

2007-08-16T13:36:26Z

‎Potential Participants

Papadopo: /* Potential Participants */

2007-08-16T13:36:04Z

‎Potential Participants

Uchiyama: /* Comments/Discussion */

2007-08-14T03:43:11Z

‎Comments/Discussion

Uchiyama: /* Comments/Discussion */

2007-08-14T03:41:59Z

‎Comments/Discussion

Uchiyama: /* Comments/Discussion */

2007-08-14T03:40:24Z

‎Comments/Discussion

Uchiyama: /* Comments/Discussion */

2007-08-14T03:39:59Z

‎Comments/Discussion

Andreas at 19:25, 18 July 2007

2007-07-18T19:25:34Z

Uchiyama: /* Potential Participants */

2007-07-04T12:28:12Z

‎Potential Participants

@@ Line 73: / Line 73: @@
 * Yuki Uchiyama [uchiyama at hil.t.u-tokyo.ac.jp]
 * Helene Papadopoulos (firstnamelastname@hotmail.com)
-* Heng-Tze, Cheng (mikejdionline@gmail.com)
+* Heng-Tze Cheng (mikejdionline@gmail.com)
 == Bibliography ==

@@ Line 73: / Line 73: @@
 * Yuki Uchiyama [uchiyama at hil.t.u-tokyo.ac.jp]
 * Helene Papadopoulos (firstnamelastname@hotmail.com)
 == Bibliography ==

@@ Line 72: / Line 72: @@
 * [http://www.matthiasmauch.net Matthias Mauch]
 * Yuki Uchiyama [uchiyama at hil.t.u-tokyo.ac.jp]
-* Helene Papadopoulos (firstname.lastname@hotmail.com)
+* Helene Papadopoulos (firstnamelastname@hotmail.com)
 == Bibliography ==

@@ Line 72: / Line 72: @@
 * [http://www.matthiasmauch.net Matthias Mauch]
 * Yuki Uchiyama [uchiyama at hil.t.u-tokyo.ac.jp]
 == Bibliography ==

@@ Line 105: / Line 105: @@
 From Uchiyama:
-Though this task will not be run this year, I am interested in this task.
+Though this task will not be run this year, I am interested in this task. I write some comments here.
 ) We do a frame based format, because it is easy to evaluate the 'Precision'.
 ) The set of chord proposed includes so many chords that some chords scarcely appear in the test songs. I propose the set of chord includes major, minor, major-major7, major-minor7, and minor-minor7.

← Older revision		Revision as of 03:39, 14 August 2007
Line 101:		Line 101:

	At any rate, please begin discussing topics here, so I can both start gathering data, and writing evaluation software. If someone already has some evaluation software for a task like this please share.		At any rate, please begin discussing topics here, so I can both start gathering data, and writing evaluation software. If someone already has some evaluation software for a task like this please share.
		+
		+
		+	From Uchiyama:
		+	This task will not be run this year, but if possible I want to do this task.
		+	1) We do a frame based format, because it is easy to evaluate the 'Precision'.
		+	2) The set of chord proposed includes so many chords that some chords scarcely appear in the test songs. I propose the set of chord includes major, minor, major-major7, major-minor7, and minor-minor7.

← Older revision		Revision as of 19:25, 18 July 2007
Line 88:		Line 88:

	7.Papadopoulos,H. and Peeters,G.(2007). '''Large-scale study of chord estimation algorithms based on chroma representation and HMM.''' Proceedings of 5th International Conference on Content-Based Multimedia Indexing.		7.Papadopoulos,H. and Peeters,G.(2007). '''Large-scale study of chord estimation algorithms based on chroma representation and HMM.''' Proceedings of 5th International Conference on Content-Based Multimedia Indexing.
		+
		+	== Comments/Discussion ==
		+
		+	From Andreas:
		+
		+	There are many points of discussion above which need discussion, I will reiterate some of them here:
		+
		+	Agenda of what needs to be done:
		+	1) Need to discuss and finalize the formats for the groundtruth and algorithm outputs. Do we do a frame/timestamp based format, i.e. <timestamp>,<chord> every line? We also need to discuss whether the 'precision' to which the chords are annotated. Do we go ahead and do the full set of triads and quads as proposed? Or do we simplify the task some? If we use the full set do we discount some errors?
		+
		+	2) Data sources. Katja says they have some data they can contribute. What are some other data sources? Queen Mary I believe has some Beatles songs? Should we augment collections with some synthesized/electronic pieces (where getting the ground truth would be easy from piano rolls)?
		+
		+	At any rate, please begin discussing topics here, so I can both start gathering data, and writing evaluation software. If someone already has some evaluation software for a task like this please share.