Edge Impulse Inc. / Tutorial: Responding to your voice Public

Edge Impulse Inc. / Tutorial: Responding to your voice

This is the finished Edge Impulse project for the tutorial 'Responding to your voice'. From here you acquire new training data, design impulses and train models.

Keyword spotting

About this project

Hello, World!

Speech icon on board

Have you ever wanted to make your own "Ok, Google" or "Alexa" keyword spotting model? Clone this project to build an embedded ML project detecting the "Hello World" keyword phrase.

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

Sensor & Block Information

  • Microphone audio data (.wav files) @ 16000 Hz
  • MFCC DSP block for human voice audio
  • Neural Network Classifier with prediction outputs: "helloworld", "noise", "unknown"

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.

Deploy

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
MFCC training data NPY file 1649 windows
MFCC training labels NPY file 1649 windows
MFCC testing data NPY file 413 windows
MFCC testing labels NPY file 413 windows
NN Classifier model TensorFlow Lite (float32) 17 KB
NN Classifier model TensorFlow Lite (int8 quantized) 7 KB
NN Classifier model TensorFlow SavedModel 22 KB
NN Classifier model Keras h5 model 16 KB

Clone project

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

Summary

Data collected
34m 22s

Project info

Project ID 113017
Project version 9
License No license attached