A New Single-Channel Speech Separation Method Based on Sparse Decomposition

GUO Hai-yan; YANG Zhen; ZHU Wei-ping

doi:10.3969/j.issn.0372-2112.2012.04.023

您当前的位置：

首页 >

文章列表页 >

A New Single-Channel Speech Separation Method Based on Sparse Decomposition

更新时间：2025-07-16

- A New Single-Channel Speech Separation Method Based on Sparse Decomposition
- Acta Electronica Sinica Vol. 40, Issue 4, Pages: 762-768(2012)
- 作者机构：
  
  1. 南京农业大学工学院,江苏,南京,210031
  2. 南京邮电大学"宽带无线通信与传感网技术"教育部重点实验室,江苏,南京,210003
  3. 南京农业大学工学院江苏南京,210031
  4. 南京邮电大学"宽带无线通信与传感网技术"教育部重点实验室江苏南京,210003
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2012.04.023
  CLC： TN912
- Published：2012
- 稿件说明：
移动端阅览
GUO Hai-yan, YANG Zhen, ZHU Wei-ping. A New Single-Channel Speech Separation Method Based on Sparse Decomposition[J]. Acta Electronica Sinica, 2012, 40(4): 762-768.
DOI：

GUO Hai-yan, YANG Zhen, ZHU Wei-ping. A New Single-Channel Speech Separation Method Based on Sparse Decomposition[J]. Acta Electronica Sinica, 2012, 40(4): 762-768. DOI： 10.3969/j.issn.0372-2112.2012.04.023.

摘要

论文以新的语音信号稀疏基—准KLT基的构造为基础

提出了一种新的基于稀疏分解的单通道混合语音分离方法.论文首先以理想准KLT基的构造为基础

从理论上提出并证明了基于各源语音信号的理想准KLT基

利用

exp(0)-范数优化算法

可实现单通道混合语音的完美分离.鉴于单通道混合语音分离时

无法精确求取各源语音信号的理想准KLT基

论文提出先基于正交匹配追踪算法

以混合语音信号为已知条件

构造各源语音信号的正交匹配追踪模板匹配准KLT基

再由

exp(0)-范数优化算法来分离单通道混合语音.仿真实验表明论文所提理论的正确性

和基于正交匹配追踪模板匹配准KLT基来分离单通道混合语音信号的有效性.

Abstract

This paper proposes a new single-channel speech separation method based on sparse decomposition.The new method is based on the construction algorithms of quasi-KLT bases proposed in this paper.First

it is proved that based on the ideal quasi-KLT bases generated from the sources

both sources can be perfectly separated from a single mixture by l exp(0) optimization.Then

considering the fact that the ideal quasi-KLT bases cannot be obtained in practice

orthogonal matching pursuit (OMP) template-matching quasi-KLT bases generated from the single mixture are first proposed

and then perform single-channel speech separation by l exp(0) optimization using the OMP template-matching quasi-KLT bases.Finally

simulation results demonstrating the perfect separation of both sources from a single-channel speech mixture by l exp(0) optimization using ideal quasi-KLT bases

as well as the effective performance of single-channel separation of two speech sources using the OMP template-matching quasi-KLT bases are presented.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Single Channel Audio-Visual Fusion Speech Separation Method Based on DCNN and BiLSTM

A Sparsity Adaptive Subspace Pursuit Algorithm for Compressive Sampling

A Novel Quantum Genetic Algorithm Based on Particle Swarm Optimization Method and Its Application

Speech Separation Based on Sound Localization and Auditory Masking Effect

Research on the Method of EEG Signal Denoising Based on the DIVA Model

Related Author

KANG Shou-qiang

HAN Yu-lan

GUO Xiao-xia

WANG Shun-bo

LAN Chao-feng

HU Bo

YANG Cheng

FENG Wei

Related Institution

School of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology

Electronic Engineering Department,Fudan University

西南交通大学信息科学与技术学院

School of Electronics and Information Engineering, Soochow University

Computer Department, Nanjing University of Posts and Telecommunications

⁰