Table 4 Comparison of complexity in terms of number of trainable parameters, multiplications and real-time factor (measured on an Intel Core i5 machine clocked at 3.4 GHz) for our proposed methods and the high-complexity reference pre-published in [39]. Comparisons are given for the second stage, for which the methods differ, and for the total two-stage system
From: Speech enhancement by LSTM-based noise suppression followed by CNN-based speech restoration
Method | Number of parameters [106] | Number of multiplications [106] | Real-time factor | |||
|---|---|---|---|---|---|---|
| Â | Second stage only | Total | Second stage only | Total | Second stage only | Total |
LSTM-cMSA + CLED-cSA-du [39] | 5.2 | 8.8 | 630.4 | 634.0 | 1.54 | 1.85 |
LSTM-cMSA + CED-cSA-du (new) | 3.4 | 7.0 | 509.5 | 512.1 | 0.86 | 1.14 |
LSTM-cMSA + CED-cSA-tr (new) | 3.4 | 7.0 | 364.6 | 369.2 | 0.45 | 0.68 |