David Schwarz / Acoustic Anomaly Detection - TI LaunchPad 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 Anomaly Detection - TI LaunchPad

Detect anomalous sounds of glass breaking using the DCASE rare sound events dataset: http://dcase.community/challenge2017/task-rare-sound-event-detection-results

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 (365 samples)

View all

320126.2ia6t2pv.s6

ID: 51140140

Label: glassbreak

Sample length: 1s

320126.2ia6t2pv.s13

ID: 51140144

Label: glassbreak

Sample length: 2s

noise.2ie5pe45

ID: 51139409

Label: background

Sample length: 1s

noise.2ie5qboa

ID: 51139392

Label: background

Sample length: 1s

87568.2ia6t17a.s1

ID: 51139892

Label: glassbreak

Sample length: 2s

noise.2ie5qccd

ID: 51139370

Label: background

Sample length: 1s

noise.2ie5mnkm

ID: 51139471

Label: background

Sample length: 1s

320126.2ia6t2pv.s4

ID: 51140161

Label: glassbreak

Sample length: 2s

Model accuracy (Unoptimized (float32))

Validation set

95.6%

Test set

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

Latency

60 ms.

Peak RAM usage

7.2K

Flash usage

44.0K

Run this model

On any device

Clone project

Dataset summary

Data collected

9m 37s

Sensor

audio @ 16KHz

Labels

background, glassbreak

Project info

Project ID	52625
Project version	2
License	BSD 3-Clause Clear
No. of views	35,249
No. of clones	10