You are on page 1of 12

By Om Joshi, Varun

Venkatesh, Sid Anand,


Vienna Li

Enhancing the way students


take notes
The problem:
It is harder for students
who have trouble
concentrating or learning
to take notes online

2
We have created a note taking software which provides a simple way to
take notes:

Our note taking software:


-uses speech to text translation to convert the speech into a transcript
- it also summarizes teacher’s lectures
-identifies key words and gives resources based on those words.

3
Features:
Speech recognition-
py_audio-google_audio
Used nltk for:
● Summarization
● Key word detection
4
Design sketch 5
How we achieved key word detection:
● Term Frequency – How frequently a term occurs in a text. It is measured as the number
of times a term t appears in the text / Total number of words in the document

● Inverse Document Frequency – How important a word is in a document. It is measured


as log(total number of sentences / Number of sentences with term t)
● TF-IDF – Words’ importance is measure by this score. It is measured as TF * IDF

● Essentially, what we did was calculate the word importance inside the document
● We improved our overall efficiency through stop word detection
● We used nltk to remove stop words such as “the”, “it”, “them
Key words: top 5 most important words

6
Note: We used the py_audio and
Summarization google_audio libraries for text to
Extraction-based summarization
speech translation
Based on the sentences inside the code,

NTLK is a library that is a great package that helps with natural


language processing. it stands for the Natural Language ToolKit.
Using the stopwords and word tokenization functions seperate the
sentences and find the ftrequency of certain words to help summarize
the text. Using the NLTK OC library, we integrated the summarizer

7
How We Built It

● Speech Recognition for audio transcription


● Flask for the front end
● PyAudio for microphone input
● Nltk for key word identification and summarization using
NLP
● Python for snakes

8
Demo: Let’s show you
how it works!

9
Future Plans:
Live translation in all languages
Better UI
Keyword detection(more advanced)
We didn’t have enough time to improve our front
end because our program was so complicated

We hope to deploy this web application into the real world for students like us take
notes for the critical years of high school and college effectively.

10
Challenges we faced:
- Text Summarization
- NLP libraries for keywords
- Methods of Collaboration
- Communication through
different time Zones
11
Thank you!

12

You might also like