The Classification of EMG Signals using Machine Learning for the Construction of a Silent Speech Interface

Project Abstract

With 7.5 million people unable to speak due to various conditions, patients are forced to use cumbersome/inefficient devices such as eye/cheek trackers. In this study, a speech aid known as a Silent-Speech-Interface(SSI) was created. This device could be used by patients with speech disorders to communicate letters in the English-alphabet voicelessly, merely by articulating words or sentences in the mouth without producing any sounds. The SSI records EMG signals from the speech system which are then classified into speech in real-time using a trained Machine Learning(ML) model. It was found that the SVM-ML algorithm yielded the highest SSI accuracy of 90.1% Overall, this study involves the creation of a device that measures biomedical signals and translates them into speech accurately using an ML algorithm. This study’s findings could improve the accuracy of future SSIs by identifying the most accurate algorithms for use in an SSI.

Research Paper - The Classification of EMG Signals using Machine Learning for the Construction of a Silent Speech Interface.pdf
Varun Chandrashekhar - SpeakUp - Poster.pdf

Research Publications


The Young Researcher (Peer-Reviewed Research Journal): 

Description:  I was one of 20 students in the nation to be selected for publication in "The Young Researcher" - a peer-reviewed journal dedicated to publishing the best original research from secondary school students.

HyperLink: The Young Researcher Publication


College Board:

Description: I was one of 2 students in the nation selected by the College Board, whose research work was published as a perfect scoring exemplar model for the AP Research course.

HyperLink: College Board Publication


The STEMY Innovation Journal:

Description: The STEMY nonprofit creates its own research journal. This journal presents ambitious research projects for a younger audience so that students can be inspired and more involved with STEM.

HyperLink: STEMY Innovation Journal Publication

AwardS

National:

State:

Regional: