Table 6 The training duration, inference duration, and carbon footprint of training on MIR-1K of RPCA-DRNN and reference methods
From: RPCA-DRNN technique for monaural singing voice separation
| Â | Training duration (h) | Inference duration (h) | Carbon footprint of training (kg of carbon dioxide) |
|---|---|---|---|
sRNN | 112 | 0.5 | 17 |
CRNN-A | 144 | 0.5 | 22 |
RPCA-DRNN | 224 | 0.5 | 35 |