MishMash hackathon is India’s largest online diversity hackathon. The focus will be to give you, regardless of your background, gender, sexual orientation, ethnicity, age, skill sets and viewpoints, an opportunity to showcase your talent. The Hackathon is Live from 6:00 PM, 23rd March to 11:55 PM, 1st April, 2020
Before you start, please follow this format for your issue title:
UNPAID_INTERNS - DALP - EDTECH
ℹ️ Project information
You can select any one theme from - XR / Mobility / FinTech/ Deep Tech or Machine Learning / Ed-Tech / Social Impact
Mobility, FinTech and Ed-Tech are Open Innovation Themes
XR has 3 sub-categories that you can choose from:- Epidemic, Urban, Remake
Deep Tech or Machine Learning is sponsored by UNILEVER and has 3 Problem Statements. If you pick this theme, you need to declare which problem statement you are going to work on
Social Impact has only 1 Problem Statement - So, if you pick this theme you just need to select this Theme and say you will work on the Problem Statement in the Idea Brief Field
Short Project Description: A swiss army knife solution for distance learning with support for proctoring, automatic lecture notes generation and support for low bandwidth mode
Team Name: unpaid_interns
Team Members: Bhumij Gupta(@bhumijgupta), Yash Mehrotra(@yashmeh), Allandhir Megharaj(@allandhir), Aditya Chandak(@adityachandak287)
Deep Tech - Problem Statement - 3: If you have chosen to work on the problem statement - 3 then please submit both models based on the two datasets provided to you.
Deep Tech - Problem Statement - 2: If you have chosen to work on the problem statement - 2 then please provide the reference for your dataset.
Introduction
We will be creating a web based service named DALP (Distance Academic Learning Portal) to stream teacher’s data to end-users i.e. students with the help of WebRTC, making for highly scalable and efficient transmission of the video stream to help make online learning more accessible and convenient along with necessary implementations to tackle the issues of slow internet connection.
What is our solution?
Bandwidth Compression
Taking into account, all students are not privileged enough to be endowed with high speed internet connection the portal will have the feature to send still images of the video stream every couple of seconds, rather than the real time live stream. To make up for the lost audio, the portal will provide the students with a live transcript with the help of Microsoft Azure Speech SDK for coverting speech to text.
Live Proctoring
With the advent of online classes, the miscreants of the students will increase including students not being present in the class and just turning on the stream. To combat this issue, we will deploy a client side face tracking feature, which will check if the student is present in the class at certain intervals. Absence of a student will send the notification to the teacher regarding the misconduct. The software will also check the liveliness of the face so it cannot be fooled by the still image of the student.
Live Engagement
To increase the engagement of students in the class, the teacher can also schedule live quizzes/quizzards on the portal and get the results of the user submission in the class to get a better understanding of the student’s knowledge on the topic/s.
Transcript Generation
The live conversion of the teacher’s lecture will be handled in real-time.
We will be using Microsoft Azure's cognitive service, Azure Speech SDK for converting speech to text and send transcript over socket to the students in the created class room.
The student can opt for slow internet mode, where he can see the live transcript along with still images of stream.
Lecture Notes Generation
If a student wants to go through the contents of the class once again or if a student missed out on the class, once the live lecture/session is over, the transcripts of the class which are previously stored to a DB, are used to dynamically generate a PDF with everything that was said by the instructor with auto formatting using cues that the instructor can use while giving the lecture. For example they can say “The next topic is Pythagorean Theorem” which would insert ‘Pythagorean Theorem’ as a heading in the PDF with custom styling, or if they have drawn a diagram and they want it included in the file they can say “Insert a screenshot here”, which would grab the appropriate screenshot from the talk and insert it in the PDF file. We will be using PyFPDF library in python to generate PDF files.
🔦 Any other specific thing you want to highlight?
(Optional)
✅ Checklist
Before you post the issue:
[x] You have followed the issue title format.
[x] You have mentioned the correct labels.
[x] You have provided all the information correctly.
Before you start, please follow this format for your issue title: UNPAID_INTERNS - DALP - EDTECH
ℹ️ Project information
Project Name: Distance Academic Learning Portal (DALP)
Short Project Description: A swiss army knife solution for distance learning with support for proctoring, automatic lecture notes generation and support for low bandwidth mode
Team Name: unpaid_interns
Team Members: Bhumij Gupta(@bhumijgupta), Yash Mehrotra(@yashmeh), Allandhir Megharaj(@allandhir), Aditya Chandak(@adityachandak287)
Demo Link: https://youtu.be/bHOUIv7PNXY
Repository Link(s): https://github.com/bhumijgupta/DALP
Presentation Link: https://docs.google.com/presentation/d/16YCmMV2YsVV7RM8i6hxq74m41vX9nmcNBcpOttAk0nY/edit?usp=sharing
Deep Tech - Problem Statement - 3: If you have chosen to work on the problem statement - 3 then please submit both models based on the two datasets provided to you.
Deep Tech - Problem Statement - 2: If you have chosen to work on the problem statement - 2 then please provide the reference for your dataset.
Azure Services Used- Speech cognitive service, azure functions, azure virtual machines
🔥 Your Pitch
Introduction We will be creating a web based service named DALP (Distance Academic Learning Portal) to stream teacher’s data to end-users i.e. students with the help of WebRTC, making for highly scalable and efficient transmission of the video stream to help make online learning more accessible and convenient along with necessary implementations to tackle the issues of slow internet connection.
What is our solution? Bandwidth Compression Taking into account, all students are not privileged enough to be endowed with high speed internet connection the portal will have the feature to send still images of the video stream every couple of seconds, rather than the real time live stream. To make up for the lost audio, the portal will provide the students with a live transcript with the help of Microsoft Azure Speech SDK for coverting speech to text.
Live Proctoring With the advent of online classes, the miscreants of the students will increase including students not being present in the class and just turning on the stream. To combat this issue, we will deploy a client side face tracking feature, which will check if the student is present in the class at certain intervals. Absence of a student will send the notification to the teacher regarding the misconduct. The software will also check the liveliness of the face so it cannot be fooled by the still image of the student.
Live Engagement To increase the engagement of students in the class, the teacher can also schedule live quizzes/quizzards on the portal and get the results of the user submission in the class to get a better understanding of the student’s knowledge on the topic/s.
Transcript Generation The live conversion of the teacher’s lecture will be handled in real-time. We will be using Microsoft Azure's cognitive service, Azure Speech SDK for converting speech to text and send transcript over socket to the students in the created class room. The student can opt for slow internet mode, where he can see the live transcript along with still images of stream.
Lecture Notes Generation If a student wants to go through the contents of the class once again or if a student missed out on the class, once the live lecture/session is over, the transcripts of the class which are previously stored to a DB, are used to dynamically generate a PDF with everything that was said by the instructor with auto formatting using cues that the instructor can use while giving the lecture. For example they can say “The next topic is Pythagorean Theorem” which would insert ‘Pythagorean Theorem’ as a heading in the PDF with custom styling, or if they have drawn a diagram and they want it included in the file they can say “Insert a screenshot here”, which would grab the appropriate screenshot from the talk and insert it in the PDF file. We will be using PyFPDF library in python to generate PDF files.
🔦 Any other specific thing you want to highlight?
(Optional)
✅ Checklist
Before you post the issue: