Dmitry / audio_coughing_crying_MFE 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.

audio_coughing_crying_MFE

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 (580 samples)

View all

background.22kt037g

ID: 20574417

Label: background

Sample length: 5s

background.1.wav.22njipj5.s17

ID: 20573610

Label: background

Sample length: 1s

crying.wav.22kufdi2.s24

ID: 20574218

Label: crying

Sample length: 1s

crying.wav.22kufdi2.s192

ID: 20574013

Label: crying

Sample length: 1s

coughing.wav.22kubc3q.s49

ID: 20574255

Label: coughing

Sample length: 1s

background.wav.22kuds40.s64

ID: 20573716

Label: background

Sample length: 1s

background.wav.22kuds40.s61

ID: 20573719

Label: background

Sample length: 1s

crying.wav.22kufdi2.s143

ID: 20574072

Label: crying

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

89.4%

Test set

100.0%

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

Latency

109 ms.

Peak RAM usage

12.8K

Flash usage

38.7K

Run this model

On any device

Clone project

Dataset summary

Data collected

10m 56s

Sensor

audio @ 16KHz

Labels

background, coughing, crying

Project info

Project ID	25382
Project version	2
License	No license attached
No. of views	14,358
No. of clones	38