Electronic Ears

• 

  The user interface, left room is to record, right room is to analyze.

Inspiration

We are inspired by the quote, "Key to success is clarity and not confidence". When we want to do something in a day, we plan for it, we want to do it, we work for it. But unfortunately many of us are not able to complete it and the worst thing is that no one is aware of what went wrong, when we got distracted, how did the time fly and many such questions. So, what if a laptop hears whatever you speak the entire day and analyzes it and sends it back to you ! You can not only see what you have spoken the entire day but also the analysis given the model, which says "you were distracted" or "you were not distracted". Moreover, this is a novel idea/application.

What it does

The model gives users, two options. One to start/stop recording and the other to analyze it. The user can start recording whenever he/she wants to, may be before the start of a meeting, conference or for the entire day. After that, he can see what all he has spoken, and he/her himself/herself gets an idea about what and where it went wrong. Moreover, the model also analyzes the speech and sends some feedback. We have also embedded a chatbot, that guides the user in case they face some difficulties.

How we built it

We built it using React JS for the front end and Django for the backend. We have used natural language processing, machine learning and embedded it in the back end of the website. We have also used CSS for quality animations.

Challenges we ran into

The biggest challenge was speech to text conversion. We tried a lot of methods, but there was little accuracy. Finally we made a speech to text conversion setup using API. The second challenge was to build the machine learning model. It was a very big challenge to make the machine learn by providing it quality data.

Accomplishments that we're proud of

We're happy to say that we have completed our model. It's up and running. It can be used by people to see what they are doing each and every day. It gives them a great clarity. That clarity can help reach focus.

What we learned

We have learnt a lot about Django, embedding a machine learning model in a website, API's and user interfaces that can attract users.

What's next for Electronic Ears

Currently, we are working on one more feature in this project. It's visualization. After the model analyzes the speech for every sentence and it gives feedback to user with the exact time, highlighting the line with colors and with suitable graphs. After this, we are planning for public release.

Built With

• css
• django
• machine-learning
• natural-language-processing
• react