SpeakUp - a Machine Learning based Speech Aid that Translates Brain Signals into Words
Overview
Summary: SpeakUp, an Machine Learning based speech aid was developed to allow paralyzed individuals to communicate in real-time. SpeakUp captures subtle brain signals, sent to the throat, and translates them into words. This device has an 80.1% accuracy and was developed for under $100. With 7.5 million people unable to speak due to various physical and mental 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 model. It was found that the Support Vector Machine algorithm yielded the highest SSI accuracy of 80.1% The device created measures biomedical signals and translates them into speech accurately using a Machine Learning algorithm. This study’s findings could improve the accuracy of future SSIs by identifying the most accurate algorithms for use in an SSI.
My Story
SpeakUp: A Machine Learning Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG signals to Speech
Varun Chandrashekhar || Kentucky Junior Academy of Science (KJAS)
duPont Manual High School
Keri Polevchak, Alesia Williams - teachers
Gmail: [email protected]
Video & Head Shot
SpeakUp: A Machine Learning Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG signals to Speech
Varun Chandrashekhar || Kentucky Junior Academy of Science (KJAS)
duPont Manual High School
Keri Polevchak, Alesia Williams - teachers
Gmail: [email protected]
Billboard
SpeakUp: A Machine Learning Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG signals to Speech
Varun Chandrashekhar || Kentucky Junior Academy of Science (KJAS)
duPont Manual High School
Keri Polevchak, Alesia Williams - teachers
Gmail: [email protected]
Research
SpeakUp: A Machine Learning Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG signals to Speech
Varun Chandrashekhar || Kentucky Junior Academy of Science (KJAS)
duPont Manual High School
Keri Polevchak, Alesia Williams - teachers
Gmail: [email protected]
Additional Items
SpeakUp: A Machine Learning Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG signals to Speech
Varun Chandrashekhar || Kentucky Junior Academy of Science (KJAS)
duPont Manual High School
Keri Polevchak, Alesia Williams - teachers
Gmail: [email protected]
Images (21)
Awards (1)
- AJAS Fellows Badge
Competition history
- AJAS 2022
Resources
Related projects
ISEF · 2021
SpeakUp: A Machine Learning-Based Speech Aid to Enable Real-Time Silent Communication for the Paralyzed by Translating Neuromuscular EMG Signals to Speech
ISEF · 2026
Beyond Audio: A Multimodal EMG-Visual Speech System for Reconstructing Voice From Silence
ISEF · 2023
Enabling Verbal Communication Through a Novel Usage of Brain-Computer Interfaces for the Differently Abled
ISEF · 2021
WAV: A Novel Subvocalization Interpretation Device
CWSF · 2026
Silent Speech Decoding for Dysarthria Using sEMG
ISEF · 2022
Enabling Oral Communication and Accelerating Recovery: The Creation of a Novel Low-Cost Electroencephalography-Based Brain-Computer Interface for the Differently Abled
CWSF · 2026
MyoVoice: A Low-Cost Facial EMG Wearable for Nonverbal Communication
JSHS · 2024
Language Models as Catalysts in EEG-Based BCI Speller Systems: A Low-Cost Solution for Paralyzed Patients
Closest projects by meaning, across every fair and year in the corpus.