Ricardo / Applied TinyML > Sound Classification > 2.3 > Voice Commands Public

Target: Cortex-M4F 80MHz Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Applied TinyML > Sound Classification > 2.3 > Voice Commands

Keyword spotting

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (6,157 samples)

View all

noise.orig_train.VacuumCleaner_5.wav.9000

ID: 454539900

Label: noise

Sample length: 1s

noise.orig_train.NeighborSpeaking_6.wav.107000

ID: 454537968

Label: noise

Sample length: 1s

yes.64df20d8_nohash_3

ID: 454533296

Label: yes

Sample length: 1s

noise.orig_train.Babble_5.wav.6000

ID: 454538222

Label: noise

Sample length: 1s

noise.orig_train.Babble_4.wav.13000

ID: 454537822

Label: noise

Sample length: 1s

yes.fb7eb481_nohash_1

ID: 454533700

Label: yes

Sample length: 1s

yes.bc065a17_nohash_0

ID: 454532400

Label: yes

Sample length: 1s

noise.orig_train.ShuttingDoor_2.wav.25000

ID: 454539746

Label: noise

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

89.7%

Test set

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

180 ms.

Peak RAM usage

13.0K

Flash usage

27.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

1h 43m 56s

Sensor

audio @ 16KHz

Labels

dianna, luna, no, noise, unknown, yes

Project info

Project ID	277828
License	3-Clause BSD
No. of views	29,340
No. of clones	0