Skip to main content

Table 6 Multi-condition (MC) classification results of different algorithms with e-scaled weight ensemble learning (-e) at the second-stage TsEL (unit: %)

From: Robust sound event classification with bilinear multi-column ELM-AE and two-stage ensemble learning

  Clean 20 dB 10 dB 0 dB Mean
DNN 94.70 95.80 92.10 87.70 92.58
ELM 93.91 ± 0.71 94.34 ± 0.61 93.90 ± 0.86 91.51 ± 0.91 93.42 ± 0.77
ELM-AE 94.50 ± 1.04 94.48 ± 1.04 94.50 ± 0.77 93.68 ± 0.94 94.29 ± 0.95
B-ELM-AE 96.95 ± 0.66 96.50 ± 0.46 96.48 ± 0.58 95.45 ± 0.53 96.35 ± 0.56
MC-ELM-AE-C 95.60 ± 0.94 95.53 ± 0.67 95.83 ± 0.61 94.58 ± 0.90 95.39 ± 0.78
MC-ELM-AE-TsEL-V 95.28 ± 0.69 95.23 ± 0.43 95.55 ± 0.79 94.40 ± 0.92 95.11 ± 0.71
MC-ELM-AE-TsEL-W 96.13 ± 0.61 96.38 ± 0.64 96.50 ± 0.63 95.35 ± 0.66 96.09 ± 0.64
B-MC-ELM-AE-C 96.53 ± 0.49 96.33 ± 0.62 96.43 ± 0.53 95.68 ± 0.77 96.24 ± 0.60
B-MC-ELM-AE-TsEL-V 96.73 ± 0.63 96.73 ± 0.46 96.53 ± 0.83 95.60 ± 0.58 96.39 ± 0.62
B-MC-ELM-AE-TsEL-W 97.43 ± 0.65 97.35 ± 0.43 97.20 ± 0.78 96.40 ± 0.36 97.10 ± 0.56