Speech Detection and Noise Compression Based on Singularity

DOI

10.2991/ameii-15.2015.136How to use a DOI?

Keywords

noise compression; wavelet packet; singularity; speech detect; algorithm.

Abstract

Frequencies of traffic noise are near to or even the same as speech signal. It is hard to filter noise from speech. Wavelet packet decomposition coefficient reveals singularity of signal. Constructed a wavelet according to Daubechies' method, and derived a wavelet packet from the constructed scaling and wavelet functions. Analyzed singularity measurement of speech signal and noise. Decomposed the noisy speech signal by wavelet packet. Developed algorithm to detect starting and ending point of speech; Developed algorithm to compress noise by wavelet packet. Reconstructed the wavelet packet tree. Re-built audio file using reconstructed data and the result is acceptable.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Haitao Luo
PY  - 2015/04
DA  - 2015/04
TI  - Speech Detection and Noise Compression Based on Singularity
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 729
EP  - 734
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.136
DO  - 10.2991/ameii-15.2015.136
ID  - Luo2015/04
ER  -