Hizketa-interfaze isilak: ahotsaren sorrera bioseinaleetatik. Seinale elektromiografikoen bidezko azterketa Silent Speech Interfaces: generation of speech from biosignals. A study with electromyographic signals.
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Silent Speech Interfaces (SSI) are devices that are capable of decoding speech from non-acoustic biosignals. These devices have multiple applications, one of which is to serve as a communication support for people with speech disabilities. There are several types of SSI depending on the type of biosignal used: they can include vocal tract imaging, electromyography (EMG), ultrasound, electroencephalography (EEG) and magnetoencephalography (MEG). This paper describes the experiments performed for the design of an EMG signal-based SSI with the aim of restoring voice in laryngectomized individuals. Preliminary results indicate that it is possible to obtain intelligible speech from EMG signals, although further research is needed to improve accuracy and effectiveness. In addition, new techniques and databases are being explored to improve these systems.
##plugins.themes.bootstrap3.article.details##
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.