Samples from "F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech
Enhancement"
Authors: Shimin Zhang, Yuxiang Kong, Shubo Lv, Yanxin Hu, Lei Xie
Part1: Blind test by Interspeech AEC-challenge 2021
Double-talk scenario
| Model |
Sample 1 |
Sample 2 |
Sample 3 |
Sample 4 |
Sample 5 |
| Microphone signal |
|
|
|
|
|
| Reference signal |
|
|
|
|
|
| Webrtc-AEC3 |
|
|
|
|
|
| BLSTM |
|
|
|
|
|
| AEC-challenge baseline |
|
|
|
|
|
| DCCRN-AEC |
|
|
|
|
|
| DTLN-AEC |
|
|
|
|
|
| DC-F-T-LSTM-CLSTM |
|
|
|
|
|
Near-end single-talk scenario
| Model |
Sample 1 |
Sample 2 |
Sample 3 |
Sample 4 |
Sample 5 |
| Microphone signal |
|
|
|
|
|
| Reference signal |
|
|
|
|
|
| Webrtc-AEC3 |
|
|
|
|
|
| BLSTM |
|
|
|
|
|
| AEC-challenge baseline |
|
|
|
|
|
| DCCRN-AEC |
|
|
|
|
|
| DTLN-AEC |
|
|
|
|
|
| DC-F-T-LSTM-CLSTM |
|
|
|
|
|
Far-end single-talk scenario
| Model |
Sample 1 |
Sample 2 |
Sample 3 |
Sample 4 |
Sample 5 |
| Microphone signal |
|
|
|
|
|
| Reference signal |
|
|
|
|
|
| Webrtc-AEC3 |
|
|
|
|
|
| BLSTM |
|
|
|
|
|
| AEC-challenge baseline |
|
|
|
|
|
| DCCRN-AEC |
|
|
|
|
|
| DTLN-AEC |
|
|
|
|
|
| DC-F-T-LSTM-CLSTM |
|
|
|
|
|
Part2: Synthetic test dataset
Double-talk with clean near-end signal
| Model |
Sample 1 |
Sample 2 |
Sample 3 |
Sample 4 |
Sample 5 |
| Microphone signal |
|
|
|
|
|
| Reference signal |
|
|
|
|
|
| Label signal |
|
|
|
|
|
| Webrtc-AEC3 |
|
|
|
|
|
| BLSTM |
|
|
|
|
|
| AEC-challenge baseline |
|
|
|
|
|
| DCCRN-AEC |
|
|
|
|
|
| DTLN-AEC |
|
|
|
|
|
| DC-F-T-LSTM-CLSTM |
|
|
|
|
|
Double-talk with noisy near-end signal
| Model |
Sample 1 |
Sample 2 |
Sample 3 |
Sample 4 |
Sample 5 |
| Microphone signal |
|
|
|
|
|
| Reference signal |
|
|
|
|
|
| Label signal |
|
|
|
|
|
| Webrtc-AEC3 |
|
|
|
|
|
| BLSTM |
|
|
|
|
|
| AEC-challenge baseline |
|
|
|
|
|
| DCCRN-AEC |
|
|
|
|
|
| DTLN-AEC |
|
|
|
|
|
| DC-F-T-LSTM-CLSTM |
|
|
|
|
|