Edge Impulse Inc. / Tutorial: Recognize sounds from audio Public

Edge Impulse Inc. / Tutorial: Recognize sounds from audio

This is the finished Edge Impulse project for the tutorial 'Recognize sounds from audio'. From here you acquire new training data, design impulses and train models.

Keyword spotting

About this project

Running Sink Faucet Detection

Sink faucet

Have you ever wanted to know if you left an appliance running while you were away from home? Clone this project to build an embedded ML project detecting when your sink's faucet is still running with incoming audio data!

You can also follow our tutorial to guide you through building your continuous audio recognition model, from data collection to deployment on embedded devices.

Sensor & Block Information

  • Microphone audio data (.wav files) @ 16000 Hz
  • MFE DSP block for non-human voice audio
  • Neural Network Classifier with prediction outputs: "faucet", "noise"

Creating your first impulse (100% complete)

Acquire data

Every Machine Learning project starts with data. You can capture data from a development board or your phone, or import data you already collected.

Design an impulse

Teach the model to interpret previously unseen data, based on historical data. Use this to categorize new data, or to find anomalies in sensor readings.


Package the complete impulse up, from signal processing code to trained model, and deploy it on your device. This ensures that the impulse runs with low latency and without requiring a network connection.

Download block output

Title Type Size
Spectrogram training data NPY file 2687 windows
Spectrogram training labels NPY file 2687 windows
Spectrogram testing data NPY file 394 windows
Spectrogram testing labels NPY file 394 windows
NN Classifier model TensorFlow Lite (float32) 14 KB
NN Classifier model TensorFlow Lite (int8 quantized) 7 KB
NN Classifier model TensorFlow SavedModel 18 KB
NN Classifier model Keras h5 model 13 KB

Clone project

You are viewing a public Edge Impulse project. Clone this project to add data or make changes.


Data collected
15m 40s

Project info

Project ID 14301
Project version 7
License No license attached