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 | |||
---|---|---|---|---|---|---|
 | 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 |