paper-with-me

홈 › Papers

A light-weight full-band speech enhancement model

2022-06-29 · Qinwen Hu, Zhongshu Hou, Xiaohuai Le, Jing Lu

Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated strategies, i.e., a learnable spectral compression mapping for more effective high-band spectral information compression, and the utilization of the multi-head attention mechanism for more effective modeling of the global spectral pattern. Experiments validate the efficacy of the proposed strategies and show that the proposed model achieves competitive performance with only 0.89M parameters.

📄 PDF Abstract BibTeX arXiv:2206.14524

Code (1)

qinwen-hu/dparn 공식 구현 pytorch

Tasks

Speech Enhancement

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model

2023-06-01 · Xiaohuai Le, Tong Lei, Li Chen, Yiqing Guo 외

With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filter…

RetrievalSpeech Enhancement

LMFCA-Net: A Lightweight Model for Multi-Channel Speech Enhancement with Efficient Narrow-Band and Cross-Band Attention

2025-02-17 · Yaokai Zhang, Hanchen Pei, Wanqi Wang, Gongping Huang

Deep learning based end-to-end multi-channel speech enhancement methods have achieved impressive performance by leveraging sub-band, cross-band, and spatial information. However, these methods often demand substantial co…

Speech Enhancement

FSPEN: AN ULTRA-LIGHTWEIGHT NETWORK FOR REAL TIME SPEECH ENAHNCMENT

2024-04-15 · Conference 2024 4 · Lei Yang1, Wei Liu1, Ruijie Meng1, Gunwoo Lee2 외

Deep learning-based speech enhancement methods have shown promising result in recent years. However, in practical applications, the model size and computational complexity are important factors that limit their use in en…

Speech Enhancement

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

2022-03-23 · Jun Chen, Zilin Wang, Deyi Tuo, Zhiyong Wu 외

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 pro…

Speech Enhancement

DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration

2025-05-29 · Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper

In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to…

Speech Enhancement