计算机与数字工程2025，Vol.53Issue(10)：2693-2696,4.DOI:10.3969/j.issn.1672-9722.2025.10.004
基于深度学习的信噪分离方法研究
Research on Methods of Speech Separation Based on Deep Learning
CAO Weifan 1ZHANG Erhua1
作者信息
- 1. School of Computer Science and Engineering,Nanjing University of Science&Technology,Nanjing 210094
- 折叠
摘要
Abstract
Aiming at the problem of monaural speech signal-to-noise separation,a method based on deep learning is used.The speech information contains in the high-frequency part and the low-frequency part of the speech is compared.Only the low-fre-quency part of the speech is used to train the deep learning model,and better separation results are obtained.According to the differ-ence of the separation effect of the speech with stationary noise or paroxsive noise,the phenomenon of crosstalk in the separation re-sults is studied.Griffin-lim algorithm is used to reconstruct the separated speech and smooth the amplitude to eliminate channeling.关键词
信噪分离/深度学习/窜音现象Key words
signal-noise separation/deep learning/crosstalk phenomenon分类
信息技术与安全科学引用本文复制引用
CAO Weifan,ZHANG Erhua..基于深度学习的信噪分离方法研究[J].计算机与数字工程,2025,53(10):2693-2696,4.
