2014:Symbolic Melodic Similarity Results - Revision history

Kahyun Choi: /* Friedman Test with Multiple Comparisons Results (p=0.05) */

2014-10-18T01:52:26Z

‎Friedman Test with Multiple Comparisons Results (p=0.05)

Kahyun Choi at 01:52, 18 October 2014

2014-10-18T01:52:13Z

Kahyun Choi: /* Summary Results */

2014-10-18T01:51:17Z

‎Summary Results

Kahyun Choi: /* General Legend */

2014-10-18T01:25:16Z

‎General Legend

Kahyun Choi: /* General Legend */

2014-10-18T01:23:35Z

‎General Legend

Kahyun Choi: /* General Legend */

2014-10-17T17:59:43Z

‎General Legend

Kahyun Choi: /* General Legend */

2014-10-17T17:59:14Z

‎General Legend

Kahyun Choi: /* Evalutron 6000 Summary Data */

2014-10-17T17:52:55Z

‎Evalutron 6000 Summary Data

Kahyun Choi at 16:45, 17 October 2014

2014-10-17T16:45:37Z

Yun Hao: Created page with "==Introduction== These are the results for the 2013 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the [[201..."

2014-01-07T21:33:59Z

Created page with "==Introduction== These are the results for the 2013 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the [[201..."

New page

==Introduction==
These are the results for the 2013 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the [[2013:Symbolic Melodic Similarity]] page.

Each system was given a query and returned the 10 most melodically similar songs from those taken from the Essen Collection (5274 pieces in the MIDI format; see [http://www.esac-data.org/ ESAC Data Homepage] for more information). For each query, we made four classes of error-mutations, thus the set comprises the following query classes:

* 0. No errors
* 1. One note deleted
* 2. One note inserted
* 3. One interval enlarged
* 4. One interval compressed

For each query (and its 4 mutations), the returned results (candidates) from all systems were then grouped together (query set) for evaluation by the human graders. The graders were provide with only heard perfect version against which to evaluate the candidates and did not know whether the candidates came from a perfect or mutated query. Each query/candidate set was evaluated by 1 individual grader. Using the Evalutron 6000 system, the graders gave each query/candidate pair two types of scores. Graders were asked to provide 1 categorical score with 3 categories: NS,SS,VS as explained below, and one fine score (in the range from 0 to 100).

====Evalutron 6000 Summary Data====
'''Number of evaluators''' = 6 
'''Number of evaluations per query/candidate pair''' = 1 
'''Number of queries per grader''' = 1 
'''Total number of unique query/candidate pairs graded''' = 388 
'''Average number of query/candidate pairs evaluated per grader: 67 
'''Number of queries''' = 6 (perfect) with each perfect query error-mutated 4 different ways = 30 

== General Legend ==
{| border="1" cellspacing="0" style="text-align: left; width: 800px;"
|- style="background: yellow"
! width="80" | Sub code
! width="200" | Submission name
! width="80" style="text-align: center;" | Abstract
! width="540" | Contributors
|-

! JU1
| ShapeH || style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/JU1.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
|-

! JU2
| ShapeTime || style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2013/JU2.pdf PDF] || [http://julian-urbano.info Julián Urbano]
|-

! JU3
| Time || style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2013/JU3.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
|-

! RTBB1
| ATIC_SMS_2013 || style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/RTBB1.pdf PDF] || [http://www.ic.uma.es Carles Roig], [http://www.atic.uma.es Lorenzo J. Tardón],[http://www.ic.uma.es Ana María Barbancho], [http://www.atic.uma.es Isabel Barbancho]
|-

! YHKH1

| sys-IRM || style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/YHKH1.pdf PDF] ||[http://music.iit.tsukuba.ac.jp/ Sakurako Yazawa], [http://music.iit.tsukuba.ac.jp/ Yuhei Hasegawa ],[http://music.iit.tsukuba.ac.jp/ Kouhei Kanamori], [http://music.iit.tsukuba.ac.jp/ Masatoshi Hamanaka ]
|-

|}

====Broad Categories====
'''NS''' = Not Similar 
'''SS''' = Somewhat Similar 
'''VS''' = Very Similar 

====Table Headings ====
'''ADR''' = Average Dynamic Recall 
'''NRGB''' = Normalize Recall at Group Boundaries 
'''AP''' = Average Precision (non-interpolated) 
'''PND''' = Precision at N Documents 

===Calculating Summary Measures===
'''Fine'''(1) = Sum of fine-grained human similarity decisions (0-100). 
'''PSum'''(1) = Sum of human broad similarity decisions: NS=0, SS=1, VS=2. 
'''WCsum'''(1) = 'World Cup' scoring: NS=0, SS=1, VS=3 (rewards Very Similar). 
'''SDsum'''(1) = 'Stephen Downie' scoring: NS=0, SS=1, VS=4 (strongly rewards Very Similar). 
'''Greater0'''(1) = NS=0, SS=1, VS=1 (binary relevance judgment). 
'''Greater1'''(1) = NS=0, SS=0, VS=1 (binary relevance judgment using only Very Similar). 

(1)Normalized to the range 0 to 1.

==Summary Results==
===Overall Scores (Includes Perfect and Error Candidates)===
<csv>2013/sms/report_all.csv</csv>

===Scores by Query Error Types===
====No Errors====
<csv>2013/sms/No_Errors.csv</csv>
====Note Deletions====
<csv>2013/sms/Deleted.csv</csv>
====Note Insertions====
<csv>2013/sms/Inserted.csv</csv>
====Enlarged Intervals====
<csv>2013/sms/Enlarged.csv</csv>
====Compressed Intervals====
<csv>2013/sms/Compressed.csv</csv>

===Friedman Test with Multiple Comparisons Results (p=0.05)===
The Friedman test was run in MATLAB against the Fine summary data over the 30 queries. 
Command: [c,m,h,gnames] = multcompare(stats, 'ctype', 'tukey-kramer','estimate', 'friedman', 'alpha', 0.05);
<csv>2013/sms/sum_friedman_fine.csv</csv>

<csv>2013/sms/sms_fine_scores_friedman.csv</csv>

[[Image:2013 sms fine scores friedmans.png]]

[[Category: Results]]

@@ Line 94: / Line 94: @@
 <csv>2014/sms/sms_fine_scores_friedman.csv</csv>
-[[Image:2014 sms fine scores friedmans.png |500px]]
+[[Image:2014 sms fine scores friedmans.png |800px]]
 [[Category: Results]]

@@ Line 94: / Line 94: @@
 <csv>2014/sms/sms_fine_scores_friedman.csv</csv>
-[[Image:2014 sms fine scores friedmans.png |500]]
+[[Image:2014 sms fine scores friedmans.png |500px]]
 [[Category: Results]]

@@ Line 94: / Line 94: @@
 <csv>2014/sms/sms_fine_scores_friedman.csv</csv>
-[[Image:2014 sms fine scores friedmans.png]]
+[[Image:2014 sms fine scores friedmans.png |500]]
 [[Category: Results]]

@@ Line 45: / Line 45: @@
          ! YO1
-         |  ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YO1.pdf PDF] ||Yoshiaki OKUBO
+         | YOkuboSMS ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YO1.pdf PDF] ||Yoshiaki OKUBO
          |-

@@ Line 45: / Line 45: @@
          ! YO1
-         |  ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YO1.pdf PDF] ||[yoshiaki@ist.hokudai.ac.jp Yoshiaki OKUBO]
+         |  ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YO1.pdf PDF] ||Yoshiaki OKUBO
          |-

@@ Line 43: / Line 43: @@
          |-
-         ! RTBB1
+         ! YO1
-         | sys-IRM ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YHKH1.pdf PDF] ||[http://music.iit.tsukuba.ac.jp/ Sakurako 	Yazawa], [http://music.iit.tsukuba.ac.jp/ Yuhei Hasegawa ],[http://music.iit.tsukuba.ac.jp/ Kouhei Kanamori], [http://music.iit.tsukuba.ac.jp/ Masatoshi Hamanaka ]
+         |  ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YO1.pdf PDF] ||[http://music.iit.tsukuba.ac.jp/ Yoshiaki OKUBO]
          |-

@@ Line 16: / Line 16: @@
 '''Number of evaluations per query/candidate pair''' = 1 <br />
 '''Number of queries per grader''' = 1 <br />
-'''Total number of unique query/candidate pairs graded''' = 388 <br />
+'''Total number of unique query/candidate pairs graded''' = 436 <br />
-'''Average number of query/candidate pairs evaluated per grader: 67 <br />
+'''Average number of query/candidate pairs evaluated per grader: 73 <br />
 '''Number of queries''' = 6 (perfect) with each perfect query error-mutated 4 different ways = 30<br />

@@ Line 1: / Line 1: @@
 ==Introduction==
-These are the results for the 2013 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the [[2013:Symbolic Melodic Similarity]] page.
+These are the results for the 2014 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the [[2014:Symbolic Melodic Similarity]] page.
 Each system was given a query and returned the 10 most melodically similar songs from those taken from the Essen Collection (5274 pieces in the MIDI format; see [http://www.esac-data.org/  ESAC Data Homepage] for more information). For each query, we made four classes of error-mutations, thus the set comprises the following query classes:
@@ Line 30: / Line 30: @@
          ! JU1
-         | ShapeH ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/JU1.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
+         | ShapeH ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/JU1.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
          |-
          ! JU2
-         | ShapeTime ||  style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2013/JU2.pdf PDF] || [http://julian-urbano.info Julián Urbano]
+         | ShapeTime ||  style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2014/JU2.pdf PDF] || [http://julian-urbano.info Julián Urbano]
          |-
          ! JU3
-         | Time ||  style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2013/JU3.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
+         | Time ||  style="text-align: center;" |[https://www.music-ir.org/mirex/abstracts/2014/JU3.pdf PDF] ||[http://julian-urbano.info Julián Urbano]
          |-
          ! RTBB1
-         | ATIC_SMS_2013 ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/RTBB1.pdf PDF] || [http://www.ic.uma.es Carles Roig], [http://www.atic.uma.es Lorenzo J. Tardón],[http://www.ic.uma.es Ana María Barbancho], [http://www.atic.uma.es Isabel Barbancho]
+         | ATIC_SMS_2014 ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/RTBB1.pdf PDF] || [http://www.ic.uma.es Carles Roig], [http://www.atic.uma.es Lorenzo J. Tardón],[http://www.ic.uma.es Ana María Barbancho], [http://www.atic.uma.es Isabel Barbancho]
          |-
          ! YHKH1
-         | sys-IRM ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2013/YHKH1.pdf PDF] ||[http://music.iit.tsukuba.ac.jp/ Sakurako 	Yazawa], [http://music.iit.tsukuba.ac.jp/ Yuhei Hasegawa ],[http://music.iit.tsukuba.ac.jp/ Kouhei Kanamori], [http://music.iit.tsukuba.ac.jp/ Masatoshi Hamanaka ]
+         | sys-IRM ||  style="text-align: center;" | [https://www.music-ir.org/mirex/abstracts/2014/YHKH1.pdf PDF] ||[http://music.iit.tsukuba.ac.jp/ Sakurako 	Yazawa], [http://music.iit.tsukuba.ac.jp/ Yuhei Hasegawa ],[http://music.iit.tsukuba.ac.jp/ Kouhei Kanamori], [http://music.iit.tsukuba.ac.jp/ Masatoshi Hamanaka ]
          |-
@@ Line 77: / Line 77: @@
 ==Summary Results==
 ===Overall Scores (Includes Perfect and Error Candidates)===
-<csv>2013/sms/report_all.csv</csv>
+<csv>2014/sms/report_all.csv</csv>
 ===Scores by Query Error Types===
 ====No Errors====
-<csv>2013/sms/No_Errors.csv</csv>
+<csv>2014/sms/No_Errors.csv</csv>
 ====Note Deletions====
-<csv>2013/sms/Deleted.csv</csv>
+<csv>2014/sms/Deleted.csv</csv>
 ====Note Insertions====
-<csv>2013/sms/Inserted.csv</csv>
+<csv>2014/sms/Inserted.csv</csv>
 ====Enlarged Intervals====
-<csv>2013/sms/Enlarged.csv</csv>
+<csv>2014/sms/Enlarged.csv</csv>
 ====Compressed Intervals====
-<csv>2013/sms/Compressed.csv</csv>
+<csv>2014/sms/Compressed.csv</csv>
 ===Friedman Test with Multiple Comparisons Results (p=0.05)===
 The Friedman test was run in MATLAB against the Fine summary data over the 30 queries.<br />
 Command: [c,m,h,gnames] = multcompare(stats, 'ctype', 'tukey-kramer','estimate', 'friedman', 'alpha', 0.05);
-<csv>2013/sms/sum_friedman_fine.csv</csv>
+<csv>2014/sms/sum_friedman_fine.csv</csv>
-<csv>2013/sms/sms_fine_scores_friedman.csv</csv>
+<csv>2014/sms/sms_fine_scores_friedman.csv</csv>
-[[Image:2013 sms fine scores friedmans.png]]
+[[Image:2014 sms fine scores friedmans.png]]
 [[Category: Results]]