Dmitry / audio_scene_MFE_Conv1D v2 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_scene_MFE_Conv1D v2

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 (536 samples)

View all

background.1t2n9g28.s1

ID: 8111970

Label: background

Sample length: 1s

gunshots3.wav.1tb1132n.s26

ID: 8111807

Label: gunshots

Sample length: 1s

glass_breaking2.wav.1tb10ahj.s29

ID: 8111839

Label: glass_breaking

Sample length: 1s

background.1tavrojl.s1

ID: 8111957

Label: glass_breaking

Sample length: 1s

background.1t2n6s13

ID: 8112291

Label: background

Sample length: 4s

glass_breaking1.wav.1t31lp6n.s21

ID: 8111999

Label: glass_breaking

Sample length: 1s

gunshots2.wav.1t308j7i.s5

ID: 8112109

Label: gunshots

Sample length: 1s

glass_breaking.wav.1t30937v.s20

ID: 8112132

Label: glass_breaking

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

83.7%

Test set

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

Latency

144 ms.

Peak RAM usage

25.2K

Flash usage

41.3K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

9m 54s

Sensor

audio @ 8KHz

Labels

background, barking, glass_breaking, gunshots

Project info

Project ID	17194
Project version	1
License	No license attached
No. of views	13,584
No. of clones	29