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

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"
noise.orig_train.SqueakyChair_7.wav.14000.wav.1ncrodhl
helloworld.aurelien.wav.1ncrrdp9.s15
helloworld.mathijs2.wav.1ncrr8ab.s15
unknown.f35eedd7_nohash_0.wav.1ncrnr1i
helloworld.aurelien.wav.1ncrrdp9.s77
helloworld.jan3.wav.1ncrqvip.s2
unknown.017c4098_nohash_2.wav.1ncrnjqj
unknown.87014d40_nohash_2.wav.1ncrnpk2

Run this model

Scan QR code or launch in browser

Dataset summary

Data collected
34m 22s
Sensor
audio @ 16KHz
Labels
helloworld, noise, unknown

Project info

Project ID 14225
Project version 10
License BSD 3-Clause Clear
No. of views 265,389
No. of clones 464