Leonardo Chistè / speaker recognition 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

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 (1,658 samples)

View all

me.60tg0ece.s10

ID: 2138126217

Label: me

Sample length: 1s

noise.orig_test.AirConditioner_9.wav.0.wav.1ncro4cm.ingestion-675cdb5cc7-q6zp6

ID: 2137793282

Label: noise

Sample length: 1s

noise.orig_train.AirportAnnouncements_2.wav.103000.wav.1ncroavo.ingestion-675cdb5cc7-q6zp6

ID: 2137793018

Label: noise

Sample length: 1s

me.60tfn71h.s8

ID: 2138124342

Label: me

Sample length: 1s

me.60td81qg.s14

ID: 2138104432

Label: me

Sample length: 1s

me.60teuubu.s14

ID: 2138115851

Label: me

Sample length: 1s

944

ID: 2138103558

Label: notme

Sample length: 1s

me.60tf86it.s7

ID: 2138117811

Label: me

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

81.9%

Test set

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

Latency

261 ms.

Peak RAM usage

15.4K

Flash usage

31.7K

Run this model

On any device

Clone project

Dataset summary

Data collected

27m 39s

Sensor

audio @ 16KHz

Labels

me, noise, notme

Project info

Project ID	750711
License	3-Clause BSD
No. of views	7
No. of clones	0