Audio classification using ESP32 and INMP441 microphone to detect faucet-ON. Training on EdgeImpulse using MFCC and KERAS Classifier

Question/Issue
[Describe the question or issue in detail]
I have 24 hours and I must setup ESP32 with INMP441 microphone. I want to show how I can train the model to classify faucet-ON and wish to turn-ON an LED on my bread board during inferencing when the microphone listens into faucet sound.

Project ID:
804609

Context/Use case:
Since I do not see the ESP32 in the list of devices, only the ESP-EYE, I am progressing.
but i need some guidance on how to get the EdgeImpuse to hear from my INMP441 connected to the ESP32 adn through the c-cable to my laptop

Steps Taken:

  1. ESP and INMP and LED connected correctly on the breadboard.
  2. Edge Impulse setup and Data acquisiton and Impulse design done.
  3. unsure of how to perform Live classification, and later how to push this to ESP32 ?

Expected Outcome:
ESP32 with INPM441, listens into live water-flowing and classifies audio = FAUCET-ON.
and this lights-up the LED on the bread-board.

Actual Outcome:
have soem knowlege gap

Reproducibility:

  • [ ] Always
  • [ ] Sometimes
  • [ ] Rarely

Environment:

  • Platform: [e.g., Raspberry Pi, nRF9160 DK, etc.]
  • Build Environment Details: [e.g., Arduino IDE 1.8.19 ESP32 Core for Arduino 2.0.4]
  • OS Version: [e.g., Ubuntu 20.04, Windows 10]
  • Edge Impulse Version (Firmware): [e.g., 1.2.3]
  • To find out Edge Impulse Version:
  • if you have pre-compiled firmware: run edge-impulse-run-impulse --raw and type AT+INFO. Look for Edge Impulse version in the output.
  • if you have a library deployment: inside the unarchived deployment, open model-parameters/model_metadata.h and look for EI_STUDIO_VERSION_MAJOR, EI_STUDIO_VERSION_MINOR, EI_STUDIO_VERSION_PATCH
  • Edge Impulse CLI Version: [e.g., 1.5.0]
  • Project Version: [e.g., 1.0.0]
  • Custom Blocks / Impulse Configuration: [Describe custom blocks used or impulse configuration]
    Logs/Attachments:
    [Include any logs or screenshots that may help in diagnosing the issue]

Additional Information:
[Any other information that might be relevant]

Hello @denny.mbzuai,

If you are familiar with Arduino IDE and sketches, you can also download an Arduino Library in the Deployment section of your Edge Impulse project.

We provide by default a few example available in the Arduino IDE after you import the library. You can then customize the sketches to your need.

If you prefer the ESP-IDF route, you can also use our C++ Library. You’ll find more info here: GitHub - edgeimpulse/example-standalone-inferencing-espressif-esp32: Builds and runs an exported impulse locally (ESP IDF)

Let us know how it goes!

Best,

Louis