Table 4 The impact of changing the lower and higher cutoff frequencies of the log-mel spectrogram on the performance of each detector for pathological voice signals
From: A CNN-based approach to identification of degradations in speech signals
Detectors | flow[Hz] | fhigh[kHz] | ||||||
|---|---|---|---|---|---|---|---|---|
0 | 300 | 700 | 2500 | 4.3 | 11 | 15 | Nyquist | |
Noise | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 | 1.00 ±0.00 |
Distortion | 0.99 ±0.00 | 0.98 ±0.01 | 0.98 ±0.01 | 0.98 ±0.01 | 0.97 ±0.01 | 0.98 ±0.01 | 0.97 ±0.01 | 0.99 ±0.00 |
Reverberation | 0.93 ±0.01 | 0.93 ±0.01 | 0.91 ±0.01 | 0.86 ±0.02 | 0.83 ±0.02 | 0.88 ±0.01 | 0.92 ±0.01 | 0.93 ±0.01 |