2009:Audio Genre Classification (Latin Set) Results

From MIREX Wiki
Revision as of 12:32, 13 May 2010 by IMIRSELBot (talk | contribs) (Robot: Automated text replacement (-\[\[([A-Z][^:]+)\]\] +2009:\1))

Introduction

These are the results for the 2008 running of the Audio Genre Classification (Latin Set) task. For background information about this task set please refer to the 2009:Audio Genre Classification page.

Latin Set Information: Carlos Silla (cns2 (at) kent (dot) ac (dot) uk) created our dataset of Latin popular and dance music sourced from Brazil and hand labeled by music experts. This collection is likely to contain a greater number of styles of music that will be differentiated by rhythmic characteristics than the MIREX Mixed Set dataset.

More precisely, the Latin Music Database has 3,227 audio files from 10 Latin music genres:

  • Ax├⌐
  • Bachata
  • Bolero
  • Forr├│
  • Ga├║cha
  • Merengue
  • Pagode
  • Sertaneja
  • Tango

General Legend

Team ID

ANO= Anonymous
BP1= Juan José Burred, Geoffroy Peeters (file)
BP2 = Juan José Burred, Geoffroy Peeters (tw)
CL1 = Chuan Cao, Ming Li
CL2 = Chuan Cao, Ming Li
GP = Geoffroy Peeters
GT1 = George Tzanetakis (mono)
GT2 = George Tzanetakis (stereo)
GLR1 = Andrei Grecu, Thomas Lidy, Andreas Rauber (full)
GLR2 = Andrei Grecu, Thomas Lidy, Andreas Rauber (template)
HNOS1 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcca)
HNOS2 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcck)
HNOS3 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tccl)
HNOS4 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcpk)
HW1 = Huaxin Wang
HW2 = Huaxin Wang
VA1 = Thomas Lidy, A. Grecu, Andreas Rauber, A. Pertusa, P. J. Ponce de Léon, J. M. Iñesta (WMV)
VA2 = Thomas Lidy, A. Grecu, Andreas Rauber, A. Pertusa, P. J. Ponce de Léon, J. M. Iñesta (BWWV)
LZG = Yi Liu, Tao Zheng, Yue Gao (RUC_1)
RCJ1 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ2 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ3 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ4 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RK1 = Preeti Rao, Sujeet Kini
SS = Klaus Seyerlehner, Markus Schedl
TTOS = Emiru Tsunoo, George Tzanetakis, Nobutaka Ono, Shigeki Sagayama
MTG1 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (false, rca)
MTG2 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (true, rca)
MTG3 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (false, simca)
MTG4 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (true, simca)
MTG5 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (false, svm)
MTG6 = Nicolas Wack, Enric Guaus, Cyril Laurier, Owen Meyers, Ricard Marxer, Dmitry Bogdanov, Joan Serrà, Perfecto Herrera (true, svm)
XLZZG = Jieping Xu, Yi Liu, Tao Zheng, Chao Zhen, Yue Gao (RUC_1)
XZZ = JiePing Xu, Chao Zhen, Tao Zheng (RUC_2)

Overall Summary Results

Raw Classification Accuracy Averaged Over Three Train/Test Folds

file /nema-raid/www/mirex/results/audiolatin/summary_audiolatin.csv not found

Accuracy Across Folds

file /nema-raid/www/mirex/results/audiolatin/audiolatin_Accuracy.csv not found

Accuracy Across Categories

file /nema-raid/www/mirex/results/audiolatin/audiolatin_Accuracy_Per_Class.csv not found

Friedman's Tests for Significant Differences

Classes vs. System Tukey-Kramer HSD Multi-Comparisons

The Friedman test was run in MATLAB against the average accuracy for each class. The Tukey-Kramer HSD multi-comparison data below was generated using the following MATLAB instruction. Command:
[c, m, h, gnames] = multicompare(stats, 'ctype', 'tukey-kramer', 'estimate', 'friedman', 'alpha', 0.05);

file /nema-raid/www/mirex/results/audiolatin/audiolatin_Accuracy_Per_Class.friedman.tukeyKramerHSD.csv not found

https://music-ir.org/mirex/2009/results/audiolatin/small.audiolatin_Accuracy_Per_Class.friedman.tukeyKramerHSD.png

Folds vs. Systems Tukey-Kramer HSD Multi-Comparison

The Friedman test was run in MATLAB against the accuracy for each fold. The Tukey-Kramer HSD multi-comparison data below was generated using the following MATLAB instruction. Command:
[c, m, h, gnames] = multicompare(stats, 'ctype', 'tukey-kramer', 'estimate', 'friedman', 'alpha', 0.05);

file /nema-raid/www/mirex/results/audiolatin/audiolatin_Accuracy.friedman.tukeyKramerHSD.csv not found

https://music-ir.org/mirex/2009/results/audiolatin/small.audiolatin_Accuracy.friedman.tukeyKramerHSD.png

Hierarchical-Discounted Scoring Results

Because of space considerations, the 2009:Mixed Set Hierarchical-Discounted Scoring Results are present on a separate page.

Results By Algorithm

(.tgz)

ANO= Anonymous
BP1= Juan José Burred, Geoffroy Peeters (file)
BP2 = Juan José Burred, Geoffroy Peeters (tw)
CL1 = Chuan Cao, Ming Li
CL2 = Chuan Cao, Ming Li
GP = Geoffroy Peeters
GT1 = George Tzanetakis (mono)
GT2 = George Tzanetakis (stereo)
GLR1 = A. Grecu, T. Lidy, A. Rauber (full)
GLR2 = A. Grecu, T. Lidy, A. Rauber (template)
HNOS1 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcca)
HNOS2 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcck)
HNOS3 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tccl)
HNOS4 = Takashi Hasegawa, Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (tcpk)
HW1 = Huaxin Wang
HW2 = Huaxin Wang
VA1 = T. Lidy, A. Grecu, A. Rauber, A. Pertusa, P. J. Ponce de Léon, J. M. Iñesta (WMV)
VA2 = T. Lidy, A. Grecu, A. Rauber, A. Pertusa, P. J. Ponce de Léon, J. M. Iñesta (BWWV)
LZG = Yi Liu, Tao Zheng, Yue Gao (RUC_1)
RCJ1 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ2 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ3 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RCJ4 = Jia-Min Ren, Zhi-Sheng Chen, Jyh-Shing Roger Jang
RK1 = Preeti Rao, Sujeet Kini
SS = Klaus Seyerlehner, Markus Schedl
TTOS = Emiru Tsunoo, George Tzanetakis, Nobutaka Ono, Shigeki Sagayama
MTG1 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (false, rca)
MTG2 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (true, rca)
MTG3 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (false, simca)
MTG4 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (true, simca)
MTG5 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (false, svm)
MTG6 = N. Wack, E. Guaus, C. Laurier, O. Meyers, R. Marxer, D. Bogdanov, J. Serrà, P. Herrera (true, svm)
XLZZG = Jieping Xu, Yi Liu, Tao Zheng, Chao Zhen, Yue Gao (RUC_1)
XZZ = JiePing Xu, Chao Zhen, Tao Zheng (RUC_2)

Run Times

file /nema-raid/www/mirex/results/mood.runtime.csv not found TBA