Mind Reading Speech Aid for the Paralyzed

2021 ELE Engineering Design Project (XF05)

---

Faculty Lab Coordinator

Xavier Fernando

Topic Category

Signal Processing / Communication

Preamble

Over 7.5 million people suffer from speech impediments. Conditions such as stroke ALS and cerebral palsy impair patients’ ability to speak. Speech impaired people live a very difficult life without the ability to easily express their thoughts. Some people, who can afford, rely on complicated and inefficient devices such as eye/cheek trackers. How about we provide them with a system that will speak for them directly reading their mind or brain waves and interpreting it using Machine Learning.

Objective

To design and implement a speech interface for the paralyzed. This device shall detect speech-related electrical signals from their throat and convert them into audible speech or letters or words that we can recognize.

Partial Specifications

It shall consist of an EMG recorder that shall save the signal in an SD card or another storage element.

Appropriate Machine Learning algorithm has to be used to identify spoken letters and words.

A website or Smartphone App shall be developed to display or speak out the identified letter/word.

Suggested Approach

In this project, a speech aid will be created. This device could be used by patients with speech disorders to communicate voicelessly, merely by articulating words or sentences in the mouth without producing any sounds. This device shall capture and records subtle neurological activation of the speech muscles from the surface of the skin or the EMG signals in the Speech system. These EMG signals shall then be classified into speech in real-time using a trained Machine Learning model.

See https://create.arduino.cc/projecthub/Varun_Chandrashekhar/speakup-ml-based-speech-aid-to-enable-silent-communication-ffd9f8?ref=search&ref_id=ML&offset=0 for a similar project.

Do not exactly duplicate. Develop your own unique version.

Group Responsibilities

The group is responsible for the successful completion of the overall project and the integration of various elements.

Student A Responsibilities

Machine learning algorithm

Student B Responsibilities

Muscle Sensor and recording EMG signals

Student C Responsibilities

Radio interface and communication

Student D Responsibilities

Arduino interface and integration

Course Co-requisites

To ALL EDP Students

Due to COVID-19 pandemic, in the event University is not open for in-class/in-lab activities during the Winter term, your EDP topic specifications, requirements, implementations, and assessment methods will be adjusted by your FLCs at their discretion.