Table 5 DLSD of the signals reproduced by different BWE methods
From: Audio bandwidth extension using ensemble of recurrent neural networks
Data type | HMM | EESN |
|---|---|---|
Country music | 4.4466 | 3.9017 |
Jazz music | 6.7463 | 4.8963 |
Rock music | 3.9707 | 3.2137 |
Violin solo | 2.1191 | 2.0595 |
Symphony | 3.3856 | 3.5123 |
Speech | 3.9606 | 3.8925 |
Average | 4.1048 | 3.5793 |