Speech De-noising based on Wavelet Transform and Genetic Algorithm

Tongtong Jiang, Jinyong Cheng

2015

Abstract

This paper proposes a novel speech de-noising algorithm based on wavelet transform and genetic algorithm which can be used in the field of speech recognition. First, the defects of the traditional wavelet de-noising are analysed. Then genetic algorithm is performed to automatically find the optimal threshold. Experiments are carried out on real speech signal to evaluate the performance of the de-noising algorithm. A higher signal-noise ratio is achieved in comparison with the performance of other method. The experimental results show that the algorithm of this paper has better de-noising effects than the traditional method.

References

  1. Wu Junyong, Wu Jiaxun, Zhang Ning, et al. [J]. 2012. Experimental study of wireless energy transmission based on magnetic coupled resonant modern electric power. In chinese
  2. Wu Ying,Yan Luguang,Xu Shangang. [J] 2003.A New Contactless Power Delivery System, ICEMS.
  3. Guo Huiping, Liu Xueguan. [M].2007 Electromagnetic field and electromagnetic wave, Xi'an Electronic and Science University press, Xi'an. In chinese
  4. Shen Na,Li Chang Sheng,Zhang He. [J].2012.Modeling and analysis of wireless power transmission system based on magnetic coupling resonance.Chinese Journal of Scientific In.strnment.In chinese
  5. Zhang Bao Qun , Li Xiang Long. [J].2012.Current research and practical analysis of contactless charging in electric vehicles, Electronic Measurement Technology. In chinese
Download


Paper Citation


in Harvard Style

Jiang T. and Cheng J. (2015). Speech De-noising based on Wavelet Transform and Genetic Algorithm . In Proceedings of the Information Science and Management Engineering III - Volume 1: ISME, ISBN 978-989-758-163-2, pages 504-509. DOI: 10.5220/0006029505040509


in Bibtex Style

@conference{isme15,
author={Tongtong Jiang and Jinyong Cheng},
title={Speech De-noising based on Wavelet Transform and Genetic Algorithm},
booktitle={Proceedings of the Information Science and Management Engineering III - Volume 1: ISME,},
year={2015},
pages={504-509},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006029505040509},
isbn={978-989-758-163-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Information Science and Management Engineering III - Volume 1: ISME,
TI - Speech De-noising based on Wavelet Transform and Genetic Algorithm
SN - 978-989-758-163-2
AU - Jiang T.
AU - Cheng J.
PY - 2015
SP - 504
EP - 509
DO - 10.5220/0006029505040509