What You’ll Need
- Raspberry Pi 3 Model B
- USB microphone
- Display for Raspberry Pi (Here we are using monitor)
For speech recognition and sentiment analysis, we are going to use IntelliHub , an AI cloud-platform. To use the API, we need to make an account on IntelliHub .
After logging in to your IntelliHub account, navigate to console and create an App. Once the App is created, you will get App info and API key.
You need to enable different service APIs to use them.
Building the Feedback Booth
Feedback booth uses microphone to take reviews as input, does sentiment analysis on cloud and gives sentiment as output which we will show in our monitor. We have used USB microphone to connect to the Raspberry Pi. It’s plug & play and does not need any driver installation. We will connect Raspberry Pi to the monitor using HDMI port.
- Setting Up
- Connect the USB mic into USB ports.
- Boot up Raspberry Pi Board. If it’s not set up yet, please refer this post.
- Check if the mic is recognized as a recording device by this command
- Download script from Github
If everything is fine, the result should be like below.
**** List of CAPTURE Hardware Devices ****
card 1: Device [USB PnP Sound Device], device 0: USB Audio [USB Audio]
Subdevice #0: subdevice #0
This means the USB mic is on “card 1”, “device 0”. This card number and device number will be used when you record.
Now we have everything in place to work with the Raspberry Pi and IntelliHub API, we need code. You can find feedback booth code file here.
We get two files: requirement file and feedback booth ipython notebook. To install required libraries, run the following code in terminal from directory containing downloaded files:
pip install -r requirements.txt
iPython notebook contains python code with comments. You just need to paste API key (which you got after creating an App) in the code and start running command to get sentiment of the spoken reviews.