KNOWLEDGE TRANSFER FROM WEAKLY LABELED AUDIO USING CONVOLUTIONAL NEURAL NETWORK FOR SOUND EVENTS AND SCENES. pdf

Authors: Anurag Kumar, Maksim Khadkevich, Christian Fügen


Average Precision (AP)

average Precision

Figure compared AP of \(\mathcal{N}_S\) and \(\mathcal{N}_S^{slat}\). The Index of sound events 1 to 50 is shown below. The first column is Index in the above figure, second is the event id (magenta) as used in Audioset dataset and third (blue) is sound event name

1    /m/012xff   Toothbrush
2    /m/0939n_   Gargling
3    /m/07qh7jl   Creak
4    /m/05zc1   Pulleys
5    /m/07pl1bw   Splinter
6    /m/07sx8x_   Squawk
7    /m/025_jnm   Finger snapping
8    /m/07r_80w   Hoot
9    /m/07plct2   Crushing
10    /m/08j51y   Dental drill
11    /m/07s02z0   Squeal
12    /m/07mzm6   Wheeze
13    /m/0642b4   Cupboard open or close
14    /m/023vsd   Sanding
15    /m/07q6cd_   Squeak
16    /m/08p9q4   Sidetone
17    /m/07n_g   Tuning fork
18    /m/07p78v5   Zing
19    /m/07ppn3j   Sniff
20    /m/07pt_g0   Pulse
21    /m/07pn_8q   Chopping
22    /m/07pqn27   Bouncing
23    /m/07qw_06   Wail- moan
24    /m/04fq5q   Foghorn
25    /m/0gy1t2s   Bicycle bell
26    /m/0hdsk   Chirp tone
27    /m/032n05   Whale vocalization
28    /m/01g90h   Stomach rumble
29    /m/07qs1cx   Crack
30    /m/04gxbd   electric windows
31    /m/07s34ls   Whir
32    /m/01z47d   Busy signal
33    /m/0fqfqc   Drawer open or close
34    /m/03p19w   Jackhammer
35    /m/03cl9h   Ice cream truck
36    /m/07pyy8b   Pant
37    /m/04fgwm   Electric toothbrush
38    /m/0239kh   Cowbell
39    /m/07rv4dm   Clang
40    /m/05rj2   Shuffling cards
41    /m/01lsmm   Scissors
42    /m/07plz5l   Sigh
43    /m/07r4wb8   Knock
44    /m/07s0dtb   Gasp
45    /m/0l14l2   Shofar
46    /m/03wwcy   Doorbell
47    /m/0790c   Sonar
48    /m/07r4k75   Grunt
49    /m/09f96   Mosquito
50    /m/05_wcq   Bird flight