SEMG APPROACH FOR SPEECH RECOGNITION

Speech is the most familiar and habitual way of communication used by us. Due to speech disabilities, many people find it difficult properly voice their views thus are at a disadvantage. The research tackles issue lack from impaired user recognizing with use ML models such as Gaussian Mixture Model - GMM Convolutional Neural Network CNN. With recorded cleaned muscle activity facial muscles possible predict words being uttered/whispered certain accuracy. intended system will additionally also have visual aid which can provide better accuracy when together activity-based system. Neuromuscular signals articulating using Surface Electro Myo Graphy (SEMG) sensors, be train machine learning models. In this paper we demonstrated various synthesized through ElectroMyography how they classified for visual-based lip-reading