Edge Impulse Experts / Acoustic Sensing of Worker Accidents 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.

Acoustic Sensing of Worker Accidents

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 (2,387 samples)

View all

scream.30oqnnpr.ingestion-c867f464-4d76p.s52

ID: 106532286

Label: scream

Sample length: 1s

unknown.z_openset.noise.orig_train.WasherDryer_2.wav.115000.wav.2biql5m7.eb89fd814ec1.json.2bjbplat.ingestion-7c8fd97d99-v2784.wav.30obpmuu.ingestion-c867f464-5tklj

ID: 106531213

Label: unknown

Sample length: 1s

cry.crying_9.wav.30otlcrp.ingestion-c867f464-5tklj.s7

ID: 106532925

Label: cry

Sample length: 1s

unknown.openset.NeighborSpeaking_3.wav.30obieel.ingestion-c867f464-4d76p

ID: 106531524

Label: unknown

Sample length: 1s

help.30ogikb9.ingestion-c867f464-9trqc.s72

ID: 106532449

Label: help

Sample length: 1s

scream.30oqnnpr.ingestion-c867f464-4d76p.s11

ID: 106532323

Label: scream

Sample length: 1s

scream.30oqnnpr.ingestion-c867f464-4d76p.s7

ID: 106532331

Label: scream

Sample length: 1s

help.30ogs7k2.ingestion-c867f464-5tklj.s6

ID: 106532396

Label: help

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

96.6%

Test set

92.3%

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

Latency

401 ms.

Peak RAM usage

3.8K

Flash usage

550.6K

Run this model

On any device

Clone project

Dataset summary

Data collected

39m 41s

Sensor

audio @ 16KHz

Labels

cry, help, scream, stop, unknown

Project info

Project ID	111611
Project version	1
License	No license attached
No. of views	198,535
No. of clones	66