Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling - Dissertationsschrift

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.

Product details

• Authors: Michael Wand
• Publisher: KIT Scientific Publishing
• Languages: English
• Product format: Paperback / Softback
• Released: 01.01.2015
• EAN: 9783731502111
• ISBN: 978-3-7315-0211-1
• No. of pages: 256
• Dimensions: 170 mm x 240 mm x 12 mm
• Weight: 626 g
• Illustrations: graph. Darst.
• Subjects: Guides; Natural sciences, medicine, IT, technology > IT, data processing > Miscellaneous