Reference papers
Abdulbaqi, J., Gu, Y., & Marsic, I. (2019). RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement. arXiv preprint arXiv:1904.07294.
Replication of youtube sources(KOR)
Replication of official samples
| SNR |
Source |
Noisy |
Denosing |
| 2.5 dB |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7.5 dB |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12.5 dB |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17.5 dB |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|