The performance of speech recognition systems is commonly
degraded by either speech-related disabilities or by real-world
factors such as the environmentpsilas noise level and
reverberation. In this work, we propose a subvocal speech
recognition system based on EMG signal for subvocal acquisition,
Independent Component Analysis (ICA) for feature extraction and
Neural Networks for classification. We have evaluated the
systempsilas performance using a vowel phonemes database. The
success rate was 93,99\%.
%0 Conference Paper
%1 Mendes2008-xq
%A Mendes, José A G
%A Robson, Ricardo R
%A Labidi, Sofiane
%A Barros, Allan Kardec
%B 2008 Congress on Image and Signal Processing
%D 2008
%K Speech analysis;Neural component extraction;Circuits;Filtering;Testing;Signal networks;ICA;subvocal networks;Microcontrollers;Feature processing;electromyography;neural recognition;Electromyography;Independent recognition;subvocal
%P 221--224
%T Subvocal Speech Recognition Based on EMG Signal Using
Independent Component Analysis and Neural Network MLP
%V 1
%X The performance of speech recognition systems is commonly
degraded by either speech-related disabilities or by real-world
factors such as the environmentpsilas noise level and
reverberation. In this work, we propose a subvocal speech
recognition system based on EMG signal for subvocal acquisition,
Independent Component Analysis (ICA) for feature extraction and
Neural Networks for classification. We have evaluated the
systempsilas performance using a vowel phonemes database. The
success rate was 93,99\%.
@inproceedings{Mendes2008-xq,
abstract = {The performance of speech recognition systems is commonly
degraded by either speech-related disabilities or by real-world
factors such as the environmentpsilas noise level and
reverberation. In this work, we propose a subvocal speech
recognition system based on EMG signal for subvocal acquisition,
Independent Component Analysis (ICA) for feature extraction and
Neural Networks for classification. We have evaluated the
systempsilas performance using a vowel phonemes database. The
success rate was 93,99\%.},
added-at = {2023-06-06T00:19:46.000+0200},
author = {Mendes, Jos{\'e} A G and Robson, Ricardo R and Labidi, Sofiane and Barros, Allan Kardec},
biburl = {https://www.bibsonomy.org/bibtex/2a0c2aed8fd94ab4923c8c06967716174/willwade},
booktitle = {2008 Congress on Image and Signal Processing},
interhash = {7bf1330006f58c1d8b5001f4936674ee},
intrahash = {a0c2aed8fd94ab4923c8c06967716174},
keywords = {Speech analysis;Neural component extraction;Circuits;Filtering;Testing;Signal networks;ICA;subvocal networks;Microcontrollers;Feature processing;electromyography;neural recognition;Electromyography;Independent recognition;subvocal},
month = may,
pages = {221--224},
timestamp = {2023-06-06T00:20:15.000+0200},
title = {Subvocal Speech Recognition Based on {EMG} Signal Using
Independent Component Analysis and Neural Network {MLP}},
volume = 1,
year = 2008
}