FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement

By Jun Chen, Z. Wang, Deyi Tuo, Zhiyong Wu, Shiyin Kang, Helen Mei-Ling Meng. 2022

152 citations recorded by the source corpus.

Previously proposed FullSubNet has achieved outstanding performance in Deep Noise Suppression (DNS) Challenge and attracted much attention. However, it still encounters issues such as input-output mismatch and coarse processing for frequency bands. In this paper, we propose an extended single-channel real-time speech enhancement framework called FullSubNet+ with following significant improvements. First, we design a lightweight multi-scale time sensitive channel attention (MulCA) module which adopts multi-scale convolution and channel attention mechanism to help the network focus on more discriminative frequency bands for noise reduction. Then, to make full use of the phase information in noisy speech, our model takes all the magnitude, real and imaginary spectrograms as inputs. Moreover, by replacing the long short-term memory (LSTM) layers in original full-band model with stacked temporal convolutional network (TCN) blocks, we design a more efficient full-band module called full-band extractor. The experimental results in DNS Challenge dataset show the superior performance of our FullSubNet+, which reaches the state-of-the-art (SOTA) performance and outperforms other existing speech enhancement approaches.

Subfields: Artificial Intelligence, Mechanics of Materials, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Dongchao Yang
  2. Rongjie Huang
  3. Jiatong Shi
  4. Jiang Bian
  5. Xuejiao Tan
  6. Songxiang Liu
  7. Xuankai Chang

In Signal Processing

  1. Dongchao Yang
  2. Rongjie Huang
  3. Jiatong Shi
  4. Jiang Bian
  5. Xuejiao Tan
  6. Songxiang Liu
  7. Xuankai Chang

Citations in the corpus