计算机与数字工程2019，Vol.47Issue(5)：1049-1054,6.DOI:10.3969/j.issn.1672-9722.2019.05.007
基于计算听觉场景分析的单通道信噪分离方法
Monaural Speech Separation Method Based on CASA
王凯龙 1张二华 1曹冠彬1
作者信息
- 1. 南京理工大学计算机科学与工程学院 南京 210094
- 折叠
摘要
Abstract
Based on the auditory characteristics of the human ear,combined with the distribution characteristics of the spec?trum of the speech signal,a complete set of signal separation method is established. Firstly,the pitch period of each speech frame is extracted accurately by using the method of map analysis. Then,the speaker's spectrum template is constructed based on this,the original spectrum is filtered by comb filter with appropriate window function,and the separated speech is obtained by inverse Fouri?er transform. The experimental results show that the method is effective.关键词
听觉场景分析/单通道/信噪分离/基音周期Key words
CASA/monaural/speech separation/pitch分类
信息技术与安全科学引用本文复制引用
王凯龙,张二华,曹冠彬..基于计算听觉场景分析的单通道信噪分离方法[J].计算机与数字工程,2019,47(5):1049-1054,6.
