RECOGNITION OF SPEECH SUBVOCAL BASED ON SURFACE ELECTROMYOGRAPHY (EMG SIGNAL) USING ANALYSIS OF COMPONENTS INDEPENDENT (ICA) AND NEURAL NETWORK MLP / RECONHECIMENTO DA FALA SUBVOCAL BASEADO EM ELETROMIOGRAFIA DE SUPERFÍCIE (EMG) UTILIZANDO ANÁLISE DE COMPONENTES INDEPENDENTES (ICA) E REDE NEURAL MLP

AUTOR(ES)

JOSÉ DA ASSUNÇÃO GOMES MENDES

DATA DE PUBLICAÇÃO

2007

RESUMO

The performance of speech recognition systems is commonly degraded by either speech-related disabilities or by real-world factors such as the environments noise level and reverberation. In this research, we propose a subvocal speech recognition system based on electromyography (EMG signal) for subvocal acquisition, Independent Component Analysis (ICA) for feature extraction and Neural Networks MLP for classification. We have evaluated the systems performance using a subvocal vowel phonemes database. According to the results, the methodology proposed obtained a success rate of 93.99%.

ASSUNTO(S)

rede neural electromyography subvocal speech fala subvocal eletromiografia neural network engenharia biomedica ica ica

Documentos Relacionados

• Human face recognition using MLP neural networks
• Compressão de sinais de eletrocardiograma utilizando análise de componentes independentes
• Sintese e reconhecimento da fala humana
• Reconhecimento e classificação de fáceis geológicas através da análise de componentes independentes
• Reconhecimento de fala baseado em HMM