Television station identification system based on speech forensics

DOI

10.2991/icieac-14.2014.33How to use a DOI?

Keywords

Speech processing [3],Television station identification,MFCC,BP,MATLAB

Abstract

This paper introduces the principle of speech signal processing, the method and the research status. According to the domestic and foreign relevant speech signal processing technology research [1], at the beginning of this research, we prepare enough files. Presenting a BP neural network based on MFCC recording device identification method, we began to record the audio files to be read by the first using MATLAB, and then for each file for MFCC to extract characteristic parameters [2], and then training representative voice files, establish the BP neural network recording equipment model library, then select the taped speech compared with BP neural network model libraries do, determine testing voice from which Television station.

Copyright

© 2014, 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  - Wenxiu Wang
AU  - Yunxia Zhou
AU  - Jingkai Zhou
AU  - Dongjian Cao
PY  - 2014/03
DA  - 2014/03
TI  - Television station identification system based on speech forensics
BT  - Proceedings of the 2nd International Conference on Information, Electronics and Computer
PB  - Atlantis Press
SP  - 148
EP  - 151
SN  - 1951-6851
UR  - https://doi.org/10.2991/icieac-14.2014.33
DO  - 10.2991/icieac-14.2014.33
ID  - Wang2014/03
ER  -