DNN-SpeechEnhancement-master
所属分类:Windows编程
开发工具:Python
文件大小:3KB
下载次数:5
上传日期:2019-05-13 18:31:15
上 传 者:
3822784
说明: 用自编码对语音信号去噪,有效去除相关噪声提取有用信号
(The speech signal is denoised by autoencode effectively remove relevant noise and extract useful signals)
文件列表:
DNN_sgd_lps.py (8307, 2017-08-31)
# DNN-SpeechEnhancement using Tensorflow
Use TensorFlow to realize a DNN-based speech enhancement system, which refers to the paper below:
[1] Xu Y, Du J, Dai L R, et al. A regression approach to speech enhancement based on deep neural networks[J]. IEEE/ACM Transactions on Audio Speech & Language Processing, 2015, 23(1):7-19.
Only the traning script is provided here.
Procedure:
1 Prepare you data in the form of mat format.
2 Use this script to train NN. The result will be saved in mat format.
3 In enhancement stage, just do what [1] did.
近期下载者:
相关文件:
收藏者: