Title :
Artifact removal algorithm for an EMG-based Silent Speech Interface
Author :
Wand, Michael ; Himmelsbach, Adam ; Heistermann, T. ; Janke, Matthias ; Schultz, Tanja
Author_Institution :
Cognitive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany
Abstract :
An electromygraphic (EMG) Silent Speech Interface is a system which recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. This study deals with improving the EMG signal quality by removing artifacts: The EMG signals are captured by electrode arrays with multiple measuring points. On the resulting high-dimensional signal, Independent Component Analysis is performed, and artifact components are automatically detected and removed. This method reduces the Word Error Rate of the silent speech recognizer by 9.9% relative on a development corpus, and by 13.9% relative on an evaluation corpus.
Keywords :
biomedical electrodes; electromyography; independent component analysis; medical signal processing; speech recognition; EMG signal quality; EMG-based silent speech interface; Word Error Rate; artifact components; artifact removal algorithm; automatical detection; development corpus; electric potentials; electrode arrays; electromygraphic silent speech interface; evaluation corpus; high-dimensional signal; human articulatory muscles; independent component analysis; multiple measuring points; silent speech recognizer; speech recognition; Electrodes; Electromyography; Feature extraction; Noise; Speech; Speech recognition; Training;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE
Conference_Location :
Osaka
DOI :
10.1109/EMBC.2013.6610857
