Leonardo Chistè / speaker recognition helloworld Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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.

speaker recognition helloworld

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 (2,019 samples)

View all

helloworld.mathijs1.wav.1ncrr9ig.ingestion-675cdb5cc7-tncpl.s13

ID: 2138825923

Label: unknown

Sample length: 1s

Leonardo.6101eg88.s4

ID: 2138891217

Label: Leonardo

Sample length: 1s

helloworld.mauricio6.wav.1ncrqrbc.ingestion-675cdb5cc7-q6zp6.s8

ID: 2138929585

Label: unknown

Sample length: 1s

noise.orig_test.Babble_1.wav.46000.wav.1ncro4cd.ingestion-675cdb5cc7-q6zp6

ID: 2138926592

Label: noise

Sample length: 1s

noise.orig_train.Typing_7.wav.16000.wav.1ncrocsu.ingestion-675cdb5cc7-q6zp6

ID: 2138924970

Label: noise

Sample length: 1s

noise.orig_test.AirportAnnouncements_4.wav.5000.wav.1ncro4ci.ingestion-675cdb5cc7-tncpl

ID: 2138926638

Label: noise

Sample length: 1s

Leonardo.6100gm8p.s6

ID: 2138803992

Label: Leonardo

Sample length: 1s

noise.orig_train.Babble_10.wav.1000.wav.1ncrob86.ingestion-675cdb5cc7-8nx9w

ID: 2138925964

Label: noise

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

97.5%

Test set

95.8%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

262 ms.

Peak RAM usage

15.4K

Flash usage

30.8K

Run this model

On any device

Clone project

Dataset summary

Data collected

33m 39s

Sensor

audio @ 16KHz

Labels

Leonardo, noise, unknown

Project info

Project ID	752142
License	3-Clause BSD
No. of views	107
No. of clones	0