Skip to main content

Table 5 Identification accuracy achieved by different descriptor combinations

From: Two-layer similarity fusion model for cover song identification

  Combination of HPCP and MLD    Combination of BSC and CPCP  
   MAP MaRR TOP10 MR    MAP MaRR TOP10 MR
DB801 2L-Best1 0.6064 0.4748 1394 52   2L-Best1 0.5563 0.4396 1251 72
  2L-HPCP-Best1 0.5898 0.4628 1249 61   2L-BSC-Best1 0.5394 0.4255 1233 88
  1L-HPCP-QD [32] 0.5941 0.2549 1329 61   1L-BSC-QD 0.5415 0.2344 1207 78
  1L-MLD-QD 0.2825 0.1287 663 136   1L-CPCP-QD 0.1776 0.0887 403 174
  [26] 0.5393 0.2358 1138 84   [26] 0.5393 0.2358 1138 84
  [24]   [24]
  PSO 0.4899 0.2201 1030 77   PSO 0.4732 0.2115 1031 86
  [31] 0.3939 0.1842 859 77   [31] 0.3242 0.1553 763 90
DB799 2L-Best1 0.6105 0.4901 1326 50   2L-Best1 0.5280 0.4419 1105 78
  2L-HPCP-Best1 0.5824 0.4676 1268 57   2L-BSC-Best1 0.5050 0.4204 1049 90
  1L-HPCP-QD [32] 0.5873 0.2573 1266 56   1L-BSC-QD 0.5080 0.2286 1041 83
  1L-MLD-QD 0.2922 0.1362 605 140   1L-CPCP-QD 0.1693 0.086 324 189
  [26] 0.5418 0.2313 1122 78   [26] 0.5418 0.2313 1122 78
  [24]   [24]
  PSO 0.5025 0.2280 1058 70   PSO 0.4491 0.2165 8671 99
  [31] 0.4281 0.2009 894 67   [31] 0.2963 0.1460 644 96
DB802 2L-Best1 0.5764 0.4668 1233 52   2L-Best1 0.5461 0.4469 1169 67
  2L-HPCP-Best1 0.5609 0.4515 1208 66   2L-BSC-Best1 0.5166 0.4210 1143 96
  1L-HPCP-QD [32] 0.5635 0.2469 1201 55   1L-BSC-QD 0.5234 0.2327 1140 83
  1L-MLD-QD 0.2856 0.1337 636 134   1L-CPCP-QD 0.1757 0.0870 361 192
  [26] 0.5228 0.2318 1072 82   [26] 0.5228 0.2318 1072 82
  [24]   [24]
  PSO 0.5050 0.2277 1026 63   PSO 0.4401 0.2029 920 85
  [31] 0.4280 0.1986 896 61   [31] 0.3196 0.1552 728 86
DB962 2L-Best1 0.6315 0.5440 1347 87   2L-Best1 0.5833 0.5186 1124 105
  2L-HPCP-Best1 0.6125 0.5242 1334 102   2L-BSC-Best1 0.5567 0.4921 1098 129
  1L-HPCP-QD [32] 0.6135 0.2801 1316 92   1L-BSC-QD 0.5573 0.2602 1073 105
  1L-MLD-QD 0.3417 0.1683 662 174   1L-CPCP-QD 0.2238 0.1134 389 236
  [26] 0.5856 0.2710 1170 105   [26] 0.5856 0.2710 1170 105
  [24]   [24]
  PSO 0.5452 0.2568 1098 91   PSO 0.4851 0.2336 908 111
  [31] 0.4568 0.2213 917 89   [31] 0.3627 0.1819 699 113
  1. Notes: For MAP, MaRR, and TOP10, the larger the value is, the better performance is obtained. For MR, the smaller the value is, the better performance is obtained