The problem Pratikriya - Emergency Response System solves

Our solution Pratikriya analyses the voice of the caller on live on-going calls being attended by the caller in the Emergency Response System. After analysing the voice of the caller, the solution should predict the emotional and mental condition of the caller. The solution should predict/suggest the following about the caller - stressful voice, drunk voice, prank voice, abusive voice, painful voice or any mental condition.

We are using blockchain to secure the voice data of individuals who call us in emergency due to the critical situation of the users.

Challenges we ran into

1. Audio processing was a difficult task, which included handling different audio formats and processing them to ".wav" format.

2. Setting up blockchain took us a while but we figured it out using ETH testnet, Ganache, and Truffle.

3. Acquiring testnet coins for the blockchain was a challenge.

4. Integrating API calls for audio files and livestreaming data.

5. Enhancing score of the ML model.

6. Acquiring data for ML model.