Summarize input text using a hybrid extractive-abstractive summary, convert the summary of academic material into speech format. A take on Speechify.

This capstone project was implemented during my senior year for consideration towards the bachelor degree.

Role:

Deep Learning Developer

Project Duration:

Sept 2021- Nov 2021

What did I do?

Storyboarding

Defining the workflow

Coding the module(s)

Tools:

Visual Studio Code

Google Colaboratory

GitHub

WhiteBoard

Pen and Paper

Team Members:

Avani Shrivastava

ND Bhavana

Mrs S Priya (PhD)- Guide

GitHub Repo:

GitHub - NiharikaGopinath/Summarization-and-Text-to-Speech

Writing Sample

Writing Sample.pdf

Problem Statement

A system that will be able to read long documents, summarise them effectively and then convert the text into speech; serving people unable to read (such as people with visual impairment) or even neurodivergent people who find it difficult to read large chunks of data at a time.

💻What is the project about?

A user interface that allows users to upload PDFs of academic texts to obtain an audio summary of the input text. At first, text is pre-processed from the uploaded file, the passed to the Extractive-Abstractive summarization module for a summary. This summary is then converted to an audio format.

🎯Objectives

• To compare and identify the best strategy to implement text summarisation of documents given time and resources available
• To compare and identify the best strategy to implement text to speech of the summary obtained given time and resources available
• Effective combination of both techniques and build an effective easy to use interface to improve the user experience

👩 🧑Target Audience

Students, people who want to cover large volumes of text in short durations, neurodivergent people who have trouble reading can utilize this tool

Architecture Diagram: