Update README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,7 @@ Note: The code doesn't support real-time streaming out of the box. See [issue-67
|
|
| 23 |
|
| 24 |
## Paper
|
| 25 |
|
| 26 |
-
[Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel Speech Enhancement
|
| 27 |
-
Xiang Hao, Xiaofei Li](https://arxiv.org/abs/2212.09019)
|
| 28 |
|
| 29 |
> For many speech enhancement applications, a key feature is that system runs on a real-time, latency-sensitive, battery-powered platform, which strictly limits the algorithm latency and computational complexity. In this work, we propose a new architecture named Fast FullSubNet dedicated to accelerating the computation of FullSubNet. Specifically, Fast FullSubNet processes sub-band speech spectra in the mel-frequency domain by using cascaded linear-to-mel full-band, sub-band, and mel-to-linear full-band models such that frequencies involved in the sub-band computation are vastly reduced. After that, a down-sampling operation is proposed for the sub-band input sequence to further reduce the computational complexity along the time axis. Experimental results show that, compared to FullSubNet, Fast FullSubNet has only 13\% computational complexity and 16\% processing time, and achieves comparable or even better performance.
|
| 30 |
|
|
|
|
| 23 |
|
| 24 |
## Paper
|
| 25 |
|
| 26 |
+
[Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel Speech Enhancement](https://arxiv.org/abs/2212.09019), Xiang Hao, Xiaofei Li
|
|
|
|
| 27 |
|
| 28 |
> For many speech enhancement applications, a key feature is that system runs on a real-time, latency-sensitive, battery-powered platform, which strictly limits the algorithm latency and computational complexity. In this work, we propose a new architecture named Fast FullSubNet dedicated to accelerating the computation of FullSubNet. Specifically, Fast FullSubNet processes sub-band speech spectra in the mel-frequency domain by using cascaded linear-to-mel full-band, sub-band, and mel-to-linear full-band models such that frequencies involved in the sub-band computation are vastly reduced. After that, a down-sampling operation is proposed for the sub-band input sequence to further reduce the computational complexity along the time axis. Experimental results show that, compared to FullSubNet, Fast FullSubNet has only 13\% computational complexity and 16\% processing time, and achieves comparable or even better performance.
|
| 29 |
|