Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling

Beschreibung

Speech is the natural medium of human communication, but audible speech can be overheard by bystanders and excludes speech-disabled people. This work presents a speech recognizer based on surface electromyography, where electric potentials of the facial muscles are captured by surface electrodes, allowing speech to be processed nonacoustically. A system which was state-of-the-art at the beginning of this book is substantially improved in terms of accuracy, flexibility, and robustness.
Speech is the natural medium of human communication, but audible speech can be overheard by bystanders and excludes speech-disabled people. This work presents a speech recognizer based on surface electromyography, where electric potentials of the facial muscles are captured by surface electrodes, allowing speech to be processed nonacoustically. A system which was state-of-the-art at the beginning of this book is substantially improved in terms of accuracy, flexibility, and robustness.

Autor*in

Michael Wand

Themen in »Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling«

Silent Speech Interfaces Speech Recognition Elektromyographie Electromyography Spracherkennung Silent Speech Interfaces Biosignale Biosignals

Stimmen zu »Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling«

Details

Link teilen