KIT | KIT-Bibliothek | Impressum | Datenschutz
Open Access Logo
§
Volltext
DOI: 10.5445/IR/1000041117

Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling

Wand, Michael

Abstract:
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 thesis is substantially improved in terms of accuracy, flexibility, and robustness.


Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Jahr 2014
Sprache Englisch
Identifikator URN: urn:nbn:de:swb:90-411174
KITopen-ID: 1000041117
Verlag Karlsruhe
Abschlussart Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdaten 14.01.2014
Referent/Betreuer Prof. T. Schultz
Schlagworte Electromyography, EMG-based Speech Recognition, Silent Speech interfaces
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page