Table 1 Comparison between the performance of different CNN architectures on the pathological voice data set in the form mean AUC ±95% confidence interval
From: A CNN-based approach to identification of degradations in speech signals
Detectors | CNN32 | CNN64 | CNN128 | CNN256 | CNN512 |
|---|---|---|---|---|---|
Noise | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 |
Distortion | 0.98 ±0.01 | 0.98 ±0.01 | 0.99 ±0.00 | 0.98 ±0.01 | 0.98 ±0.01 |
Reverberation | 0.90 ±0.01 | 0.91 ±0.01 | 0.93 ±0.01 | 0.91 ±0.01 | 0.89 ±0.01 |