Table 8 The retrieval performances obtained with the class vectors of an MD PSO-trained SLP classifier for both audio databases
From: An evolutionary feature synthesis approach for content-based audio retrieval
FS | Basic database (6 classes) | Extended database (12 classes) | ||
|---|---|---|---|---|
ANMRR | AP (%) | ANMRR | AP (%) | |
Segment | ||||
STAT | 0.238 | 75.0 | 0.626 | 36.4 |
MFCC | 0.101 | 89.2 | 0.518 | 47.3 |
Δ-MFCC | 0.339 | 64.7 | 0.581 | 40.0 |
ΔΔ-MFCC | 0.290 | 70.1 | 0.585 | 40.1 |
LPC | 0.491 | 49.7 | 0.673 | 31.3 |
LPCC | 0.564 | 42.3 | 0.714 | 27.4 |
S_AUDIO | 0.229 | 75.7 | 0.578 | 41.2 |
Key-frame | ||||
MFCC + deltas | 0.279 | 70.2 | 0.414 | 56.5 |
LPC + LPCC | 0.669 | 32.1 | 0.794 | 19.7 |
K_AUDIO | 0.308 | 67.7 | 0.504 | 47.1 |