← all papers · overview

Dmf-net: A Decoupling-style Multi-band Fusion Model For Full-band Speech Enhancement

2022 · Guochen Yu, Yuansheng Guan, Weixin Meng, et al.

Abstract

For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in Bark and ERB scale with relatively low frequency resolution, leading to degraded performance, especially in the high-frequency region. In this paper, we propose a decoupling-style multi-band fusion model to perform full-band speech denoising and dereverberation. Instead of optimizing the full-band speech by a single network structure, we decompose the full-band target into multi sub-band speech features and then employ a multi-stage chain optimization strategy to estimate clean spectrum stage by stage. Specifically, the low- (0-8 kHz), middle- (8-16 kHz), and high-frequency (16-24 kHz) regions are mapped by three separate sub-networks and are then fused to obtain the full-band clean target STFT spectrum. Comprehensive experiments on two public datase

Authors

(none)

Tags

  • Speech Enhancement

Stats

  • citations8
  • S2 citations—
  • github stars0
  • HF likes0
  • heat score7.16
  • arxiv keyyu2022dmf

Related papers