2005:Audio Key Finding - Revision history

CameronJones: 30 revisions

2010-05-09T22:18:45Z

30 revisions

Chinghua at 18:39, 10 February 2005

2005-02-10T18:39:00Z

Chinghua at 18:38, 10 February 2005

2005-02-10T18:38:09Z

66.215.9.142 at 09:09, 9 February 2005

2005-02-09T09:09:42Z

66.215.9.142: /* Review 1 */

2005-02-09T09:08:52Z

‎Review 1

66.215.9.142 at 09:06, 9 February 2005

2005-02-09T09:06:27Z

66.215.9.142: /* Potential Participants */

2005-02-09T09:05:05Z

‎Potential Participants

66.27.179.8: /* Review 2 */

2005-02-09T02:49:14Z

‎Review 2

66.27.179.8: /* Review 2 */

2005-02-09T02:48:36Z

‎Review 2

66.27.179.8: /* Review 2 */

2005-02-09T02:30:55Z

‎Review 2

@@ Line 70: / Line 70: @@
 [Chinghua 02.10.05]: Those relationships can be considered as the key close to the main key, still they are not the main key. But if the algorithm give those answers, it does achieve some points. So I suggest that we may give multiple levels of scores to the different answers. For example, the main key gets the whole points (may be 5), the perfect fifth gets 75% or 80% of the whole point (may be 3), and so on.
 What about tuning errors? In the case of audio, there are different tuning systems that can be used. The detection algorithm should be able to estimate where the key is "tuned" (A 440 or 442,...). Keys should be also considered as 'close' if they have a relationship of "1 semitone", to consider this difference between real key (according to its tuning) & labelled key (A major). In the case of MIDI, this problem does not appear.
 [Chinghua 02.10.05]: Since we will use MIDI synthesizer to generate the audio, the tuning won't be a serious problem. The detection algorithm should have the ability to regard both 440 and 442 Hz as pitch A. If the original piece is written in A Major but the arrangement of MIDI shifted a half step down to Ab Major, then the algorithm (both MIDI and Audio part) should detect it as Ab Major instead of A Major.
 Will it be some training data, so that participants can try their algorithms?
@@ Line 80: / Line 82: @@
 [Chinghua 02.10.05]: Some data will be provided for participants to verify their algorithms, but may be just a few pieces. Since different systems may need different amount of data for training, the participants need to find a good training data set for their own systems. Participants can use the provided data to train their systems, but the quantity and quality of the data will not be guaranteed to be good for their training purpose.
 I cannot tell whether the suggested participants are willing to participate. Other potential candidate could be: Hendrik Purwins

@@ Line 67: / Line 67: @@
-Regarding evaluation measures for audio data, it is said that "Keys will be considered as 'close' if they have one of the following relationships: distance of perfect fifth, relative major and minor, and parallel major and minor". What about tuning errors? In the case of audio, there are different tuning systems that can be used. The detection algorithm should be able to estimate where the key is "tuned" (A 440 or 442,...). Keys should be also considered as 'close' if they have a relationship of "1 semitone", to consider this difference between real key (according to its tuning) & labelled key (A major). In the case of MIDI, this problem does not appear.
+Regarding evaluation measures for audio data, it is said that "Keys will be considered as 'close' if they have one of the following relationships: distance of perfect fifth, relative major and minor, and parallel major and minor".
 Will it be some training data, so that participants can try their algorithms?
@@ Line 73: / Line 79: @@
 [Arpi 02.08.05]: Great idea!
 I cannot tell whether the suggested participants are willing to participate. Other potential candidate could be: Hendrik Purwins

← Older revision		Revision as of 09:09, 9 February 2005
Line 77:		Line 77:

	[Arpi 02.08.05]: Good addition. We have added him to the list of possible participants.		[Arpi 02.08.05]: Good addition. We have added him to the list of possible participants.
		+

	==Review 2==		==Review 2==

@@ Line 60: / Line 60: @@
 [Arpi 02.08.05]: We agree with this and believe that the best approach would be to synthesize audio data from MIDI.
 Regarding the key estimation contest from audio data, it seems that only classical music is considered. It would be possible to generalize to some other styles? For instance popular music which key is known.
 [Arpi 02.08.05]: Having test data from a variety of genres would be ideal. The advantage of classical music is that many pieces are labeled with the key name. We welcome suggestions on finding labeled music in other genres.
 Regarding evaluation measures for audio data, it is said that "Keys will be considered as 'close' if they have one of the following relationships: distance of perfect fifth, relative major and minor, and parallel major and minor". What about tuning errors? In the case of audio, there are different tuning systems that can be used. The detection algorithm should be able to estimate where the key is "tuned" (A 440 or 442,...). Keys should be also considered as 'close' if they have a relationship of "1 semitone", to consider this difference between real key (according to its tuning) & labelled key (A major). In the case of MIDI, this problem does not appear.
@@ Line 70: / Line 72: @@
 [Arpi 02.08.05]: Great idea!
 I cannot tell whether the suggested participants are willing to participate. Other potential candidate could be: Hendrik Purwins
-[Arpi 02.08.05]: Good addition.
+[Arpi 02.08.05]: Good addition. We have added him to the list of possible participants.
 ==Review 2==

@@ Line 14: / Line 14: @@
 There are significant contributions in the area of key finding for both audio and symbolic representation. This evaluation process should consider algorithms in both areas. Algorithms that determine the key from audio should be robust enough to handle frequency interferences and harmonic effects caused by the use of multiple instruments.
 ==Potential Participants==
@@ Line 32: / Line 33: @@
 * Craig Sapp (craig@ccrma.stanford.edu): [moderate].
 * David Temperley (dtemp@theory.esm.rochester.edu): [unknown].
 ==Evaluation Procedures==
@@ Line 51: / Line 53: @@
 '''Score-based Collections''': Score-based data are also symbolic representations of music. In addition to numeric event information, it also provides further pitch and time structure information such as contextually correct note names, and key and time signatures.  MusData (http://www.musedata.org), for example, provides access to such a score-based collection.
 ==Review 1==
@@ Line 71: / Line 74: @@
 [Arpi 02.08.05]: Good addition.
 ==Review 2==
@@ Line 106: / Line 110: @@
 [Arpi 02.08.05]: The Naxos collection only contains audio data. We propose using MIDI data and audio synthesized from MIDI. Please refer to comments made in Review 1.
 ==Downie's Comments==
@@ Line 118: / Line 123: @@
 [Arpi 02.08.05]: This is a great idea. This approach will certainly give us new metrics. We can further explore this if time permits.
 ==Emmanuel's Comments==
@@ Line 124: / Line 130: @@
 I am strongly in favor of merging the two proposals into a single one again. But then the symbolic and audio data need to correspond to the same titles as much as possible, so that the performances can be compared. Can the RWC database or another database be used for it ? Also the participants need to submit algorithms for both tasks if possible. I suppose it won't be too hard for audio key finding algorithms to work also on symbolic data, since audio data may be easily synthesized from symbolic data using a conventional midi synthesizer.
 ==Arpi's Comments==
 As Emmanuel stated, we submitted a single proposal for audio and symbolic key-finding. We have now re-combined the two proposals. Please refer to Emmanuels comments for further details.

← Older revision	Revision as of 22:18, 9 May 2010
(No difference)

← Older revision		Revision as of 09:05, 9 February 2005
Line 23:		Line 23:
	* Ozgur Izmirli (oizm@conncoll.edu): [moderate].		* Ozgur Izmirli (oizm@conncoll.edu): [moderate].
	* Yongwei Zhu (ywzhu@i2r.a-start.edu.sg) and Mohan Kankanhalli (mohan@comp.nus.edu.sg): [unknown].		* Yongwei Zhu (ywzhu@i2r.a-start.edu.sg) and Mohan Kankanhalli (mohan@comp.nus.edu.sg): [unknown].
		+	* Hendrik Purwins (hendrik@cs.tu-berlin.de): [unknown].

@@ Line 92: / Line 92: @@
 [Arpi 02.08.05]: Yes it is. Please refer to http://www-rcf.usc.edu/~echew/papers/CiM2003 for further details.
-[EC 02.08.05]: Keys a perfect fifth apart share all but one pitch (with the differing pitches being only one half step apart).  The above paper describes three models for tonality (by Krumhansl, Lerdahl and Chew) with similar relative distances between keys which are consistent with our proposal.
+[EC 02.08.05]: Keys a perfect fifth apart share all but one pitch (with the differing pitches being only one half step apart).  The above paper describes three models for tonality (by Krumhansl, Lerdahl and Chew) with similar relative distances between keys which are consistent with that mentioned in our proposal.
 * Parallel major or minor: Not too certain if this needs to be clarified (Ignore this comment if this is generally understood by the majority working in this field)