Zalmotek / Smart Appliance Control Using Voice Commands - Thingy:53 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.

Smart Appliance Control Using Voice Commands - Thingy:53

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 (3,409 samples)

View all

noise.orig_train.VacuumCleaner_2.wav.36000

ID: 140841466

Label: Background

Sample length: 1s

noise.orig_train.SqueakyChair_8.wav.7000

ID: 140841526

Label: Background

Sample length: 1s

Kettle.3f7q0d53.s7

ID: 140842733

Label: Kettle

Sample length: 1s

unknown.b1df80c0_nohash_1

ID: 140840918

Label: Background

Sample length: 1s

noise.orig_train.Traffic_1.wav.244000

ID: 140841634

Label: Background

Sample length: 1s

noise.orig_train.Metro_1.wav.294000

ID: 140841883

Label: Background

Sample length: 1s

noise.orig_test.Babble_7.wav.8000

ID: 140841793

Label: Background

Sample length: 1s

noise.orig_train.VacuumCleaner_9.wav.11000

ID: 140842188

Label: Background

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

99.3%

Test set

97.5%

On-device performance (Cortex-M4F 80MHz, Unoptimized (float32))

Latency

189 ms.

Peak RAM usage

16.8K

Flash usage

26.1K

Run this model

On any device

Clone project

Dataset summary

Data collected

56m 49s

Sensor

audio @ 16KHz

Labels

Background, Extractor, Kettle, Light

Project info

Project ID	145818
Project version	1
License	Apache 2.0
No. of views	173,317
No. of clones	10