Unvoiced Speech Recognition Using Dynamic Analysis of EMG Signal

The current study is an initiative taken to recognize the speech by observing the muscle associated with speech (Locks et al. in Motriz, Rio Claro 21(1):15–22, 2015, [1]). It will realize unvoiced communication; guarantee the participation of inarticulate people in society. Electromyography (EMG) sensor is used to track and recognize various intramuscular signals for accurate and precise recognition of the subjects. In this aspect, letter ‘A’ and digit ‘1’ are performed in sign language by volunteers and the EMG signals are collected for four muscles, i.e. Lumbrical muscles, Hypothenar muscles, Thenar muscles and Flexor carpi muscles of palm and hands. The nonlinear study of these signals proved to be an efficient method of sign recognition.

[1]  P. Manimegalai.  HAND GESTURE RECOGNITION BASED ON EMG SIGNALS USING ANN , 2013 .

[2]  Ferat Sahin,et al.  Real-Time American Sign Language Recognition System Using Surface EMG Signal , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[3]  L.J. Hadjileontiadis,et al.  Evaluation of surface EMG features for the recognition of American Sign Language gestures , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Jürgen Kurths,et al.  Recurrence plots for the analysis of complex systems , 2009 .

[5]  Francisco Locks,et al.  Neural adaptations in isometric contractions with EMG and force biofeedback , 2015 .

[6]  Hector Sabelli,et al.  Homeobios: the pattern of heartbeats in newborns, adults, and elderly patients. , 2010, Nonlinear dynamics, psychology, and life sciences.

[7]  Johannes Wagner,et al.  Bi-channel sensor fusion for automatic sign language recognition , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[8]  Ankur Ganguly,et al.  An Approach Towards the Representation of Sign Language by Electromyography Signals with Fuzzy Implementation , 2017 .

[9]  Anilesh Dey,et al.  Understanding the effect of cannabis abuse on the ANS and cardiac physiology of the Indian women paddy-field workers using RR interval and ECG signal analyses , 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

[10]  Roozbeh Jafari,et al.  Real-time American Sign Language Recognition using wrist-worn motion and surface EMG sensors , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[11]  Henry D I Abarbanel,et al.  False neighbors and false strands: a reliable minimum embedding dimension algorithm. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  D. Ruelle,et al.  Recurrence Plots of Dynamical Systems , 1987 .

[13]  Ferat Sahin,et al.  American Sign Language Recognition system by using surface EMG signal , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[14]  Kongqiao Wang,et al.  A Sign-Component-Based Framework for Chinese Sign Language Recognition Using Accelerometer and sEMG Data , 2012, IEEE Transactions on Biomedical Engineering.