University Program- Aalborg University: Signal Processing for Interactive Systems / Voice Emotion Mood Lamp – Maria 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.

Voice Emotion Mood Lamp – Maria

Audio

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 (409 samples)

View all

depressed.6a5qb5p1

ID: 2391578708

Label: depressed

Sample length: 3s

neutral.6b7f6ef2

ID: 2425958693

Label: neutral

Sample length: 3s

agitated.6a5qh23r

ID: 2391598520

Label: agitated

Sample length: 3s

noise.6b7fo316

ID: 2425978056

Label: noise

Sample length: 3s

agitated.6a5qgkje

ID: 2391597132

Label: agitated

Sample length: 3s

agitated.6b7f9nag

ID: 2425962068

Label: agitated

Sample length: 3s

neutral.6b7juv64

ID: 2426111527

Label: neutral

Sample length: 3s

agitated.6a8tlb1k

ID: 2394294986

Label: agitated

Sample length: 3s

Model accuracy, Phase 3 (Unoptimized (float32))

View 3 other experiments

Validation set

97.5%

Test set

97.3%

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

Latency

469 ms.

Peak RAM usage

31.4K

Flash usage

32.5K

Run this model

On any device

Clone project

Dataset summary

Data collected

20m 27s

Sensor

audio @ 16KHz

Labels

agitated, depressed, neutral, noise

Project info

Project ID	829373
License	3-Clause BSD
No. of views	1,201
No. of clones	1