2007:Audio Drum Detection - Revision history

Paulus at 12:17, 8 August 2007

2007-08-08T12:17:26Z

Alex at 17:22, 16 July 2007

2007-07-16T17:22:07Z

CameronNonAdmin: /* Proposer */

2007-07-13T15:47:27Z

‎Proposer

Paulus: /* Comments */

2007-07-03T12:09:54Z

‎Comments

Ahazan: /* Participants */

2007-06-28T17:15:39Z

‎Participants

Ahazan: /* Participants */

2007-06-21T12:05:33Z

‎Participants

Paulus: /* Participants */

2007-06-13T07:47:37Z

‎Participants

Paulus: /* Participants */

2007-06-13T07:46:38Z

‎Participants

Andreas: /* Comments */

2007-06-11T21:11:56Z

‎Comments

Andreas at 21:11, 11 June 2007

2007-06-11T21:11:28Z

@@ Line 62: / Line 62: @@
 ''Jouni:''
-This bring-your-own-model approach would be quite nice, I think. Of course it can be said that it puts participants to unequal positions since not everyone has lots of own data, but I hope this is not a problem here. I've emailed past participants, but it still seems that it is not certan that the task will be run. In any case, I will be more or less out of the office for the next month, so I hope things will clarify during that period.
+This bring-your-own-model approach would be quite nice, I think. Of course it can be said that it puts participants to unequal positions since not everyone has lots of own data, but I hope this is not a problem here. I've emailed past participants, but it still seems that it is not certan that the task will be run.
 ----

@@ Line 10: / Line 10: @@
 *Jouni Paulus (Tampere University of Technology) jouni<dot>paulus<at>tut<dot>fi
 * (potentially) Amaury Hazan (Pompeu Fabra University) ahazan<at>iua<dot>upf<dot>edu
 ==Description==

@@ Line 3: / Line 3: @@
 ==Proposer==
-Koen Tanghe (Ghent University). 2007 resurrection attempt Jouni Paulus (Tampere University of Technology)
+Jouni Paulus (Tampere University of Technology): 2007 resurrection attempt
 ==Participants==

← Older revision		Revision as of 12:09, 3 July 2007
Line 59:		Line 59:
	I think we can largely rerun this contest as it was in 2005, provided we have atleast 3 participants. I would encourage a 'bring your own model' type approach, and simply evaluate off of what we already have. I think a 'train on whatever data you have approach' is good, and shouldn't necessarily be limited to the public distribution, as it may not be expansive enough. Looking into adding some of the ENST data might be a good way to add some more data to the evaluation. I assume Olivier and Gael would possibly want to get involved once again, as Olivier believed there was some problems in his submission in 2005 that significantly impacted his performance. So Jouni, try and email past participants and let's get a discussion going here, regarding the task, and the inclusion of the ENST database, etc.		I think we can largely rerun this contest as it was in 2005, provided we have atleast 3 participants. I would encourage a 'bring your own model' type approach, and simply evaluate off of what we already have. I think a 'train on whatever data you have approach' is good, and shouldn't necessarily be limited to the public distribution, as it may not be expansive enough. Looking into adding some of the ENST data might be a good way to add some more data to the evaluation. I assume Olivier and Gael would possibly want to get involved once again, as Olivier believed there was some problems in his submission in 2005 that significantly impacted his performance. So Jouni, try and email past participants and let's get a discussion going here, regarding the task, and the inclusion of the ENST database, etc.

		+	''Jouni:''
		+	This bring-your-own-model approach would be quite nice, I think. Of course it can be said that it puts participants to unequal positions since not everyone has lots of own data, but I hope this is not a problem here. I've emailed past participants, but it still seems that it is not certan that the task will be run. In any case, I will be more or less out of the office for the next month, so I hope things will clarify during that period.
	----		----

@@ Line 8: / Line 8: @@
 *Christian Dittmar (Fraunhofer) dmr<at>idmt<dot>fraunhofer<dot>de
 *Jouni Paulus (Tampere University of Technology) jouni<dot>paulus<at>tut<dot>fi
-*Amaury Hazan (Pompeu Fabra University) ahazan<at>iua<dot>upf<dot>edu
+* (potentially) Amaury Hazan (Pompeu Fabra University) ahazan<at>iua<dot>upf<dot>edu
 ==Description==

← Older revision		Revision as of 07:46, 13 June 2007
Line 6:		Line 6:

	==Participants==		==Participants==
		+	Christian Dittmar (Fraunhofer) dmr<at>idmt<dot>fraunhofer<dot>de
	Jouni Paulus (Tampere University of Technology) jouni<dot>paulus<at>tut<dot>fi		Jouni Paulus (Tampere University of Technology) jouni<dot>paulus<at>tut<dot>fi

← Older revision		Revision as of 21:11, 11 June 2007
Line 56:		Line 56:
	''From Andreas:''		''From Andreas:''
	I think we can largely rerun this contest as it was in 2005, provided we have atleast 3 participants. I would encourage a 'bring your own model' type approach, and simply evaluate off of what we already have. I think a 'train on whatever data you have approach' is good, and shouldn't necessarily be limited to the public distribution, as it may not be expansive enough. Looking into adding some of the ENST data might be a good way to add some more data to the evaluation. I assume Olivier and Gael would possibly want to get involved once again, as Olivier believed there was some problems in his submission in 2005 that significantly impacted his performance. So Jouni, try and email past participants and let's get a discussion going here, regarding the task, and the inclusion of the ENST database, etc.		I think we can largely rerun this contest as it was in 2005, provided we have atleast 3 participants. I would encourage a 'bring your own model' type approach, and simply evaluate off of what we already have. I think a 'train on whatever data you have approach' is good, and shouldn't necessarily be limited to the public distribution, as it may not be expansive enough. Looking into adding some of the ENST data might be a good way to add some more data to the evaluation. I assume Olivier and Gael would possibly want to get involved once again, as Olivier believed there was some problems in his submission in 2005 that significantly impacted his performance. So Jouni, try and email past participants and let's get a discussion going here, regarding the task, and the inclusion of the ENST database, etc.
		+
		+	----

← Older revision		Revision as of 21:11, 11 June 2007
Line 53:		Line 53:
	*Should the systems be trained only with the provided subset or should it be allowed to utilise all data available? (I'd suggest allowing free use of any personal data.)		*Should the systems be trained only with the provided subset or should it be allowed to utilise all data available? (I'd suggest allowing free use of any personal data.)
	*If free use is not allowed, should the methods using musicological modelling be trained also only on the provided training data? (Perhaps not. It is likely that there isn't enough data to train generic enough language models.)		*If free use is not allowed, should the methods using musicological modelling be trained also only on the provided training data? (Perhaps not. It is likely that there isn't enough data to train generic enough language models.)
		+	==Comments==
		+	''From Andreas:''
		+	I think we can largely rerun this contest as it was in 2005, provided we have atleast 3 participants. I would encourage a 'bring your own model' type approach, and simply evaluate off of what we already have. I think a 'train on whatever data you have approach' is good, and shouldn't necessarily be limited to the public distribution, as it may not be expansive enough. Looking into adding some of the ENST data might be a good way to add some more data to the evaluation. I assume Olivier and Gael would possibly want to get involved once again, as Olivier believed there was some problems in his submission in 2005 that significantly impacted his performance. So Jouni, try and email past participants and let's get a discussion going here, regarding the task, and the inclusion of the ENST database, etc.