DBlindForDiscriminativeAI - Create impulse

Dwi Ahmad Dzulhijjah / DBlindForDiscriminativeAI Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) Clone this project

Impulse #1

An impulse takes raw data, uses signal processing to extract features, and then uses a learning block to classify new data.

Time series data

Input axes

audio

Window size

Window increase (stride)

Frequency (Hz)

Invalid frequency

Zero-pad data

Train on data subset

Subset % should be between 1 and 100

Audio (MFE)

Name

Input axes (1)

audio

Spectrogram

Name

Input axes (1)

Signal

Signal axis is required

Transfer learning (Keyword Spotting)

Name

Input features

MFE

Spectrogram

Output features

3 (Yelp Ambulance, Yelp Police, noise)

This block only works with an Audio (MFE) block with default parameters and a window size of 1000ms at 16000Hz, or with an Audio (Syntiant) block with default parameters and a window size of 968ms at 16000Hz.

Classification

Name

Input features

MFE

Spectrogram

Output features

3 (Yelp Ambulance, Yelp Police, noise)

Output features

6 (Yelp Ambulance, Yelp Police, noise, Yelp Ambulance, Yelp Police, noise)

Time series data

Audio (MFE)

Spectrogram

Transfer learning (Keyword Spotting)

Classification

Output features

No data collected yet