Anshuman Fauzdar / Predictive_Audio Public

Predictive_Audio

Keyword spotting

About this project

Important part of predictive maintenance includes Audio that is microphone data from devices:

Here we have 3 types of data required to clasify and predict fan noise of 3D printer [Nearest industrial machine available right now]

Background

background background-frequency

Fan Noise

fanNoise fanNoise-frequency

Fan Disturbance

fanDisturbance fanDisturbance-frequency

Type Time [m, s]
background 6m 40s
fanNoise 9m 10s
fanDisturbance 6m 40s
Total Dataset 22m 30s

Microphone Used:

Microphone

Setup:

Prototype

fanNoise.2oc0en84
fanNoise.2obvn8oh
fanNoise.2ng1ppk0
fanDisturbance.2oc1oha3
fanNoise.2ng19idf
fanNoise.2oc05s9f
fanNoise.2oc0balk
fanDisturbance.2o1c95nv

Run this model

On any device

Dataset summary

Data collected
28m 21s
Sensor
audio @ 16KHz
Labels
background, fanDisturbance, fanNoise

Project info

Project ID 63123
Project version 1
License No license attached
No. of views 11,277
No. of clones 2