AGWORKF · 04
AHMEDABADIST
VOL. 032023
SCROLL
HOME / WORK / Voicer — Sign → SpeechTinyML / on-device machine learning · 2023
— CASE 04 / TINYML · HARDWARE · NATIONAL TOP 10

VOICER —
SIGN → SPEECH.

Ten IMU rings, one wrist controller, a 12-class neural net quantized to fit in 2 KB of RAM — inferring in 2 ms, offline. Samsung Top 10 of 70,000. Featured on CNN News18.

94.1%Accuracy · 12 classes
2 msOn-device inference
55 KBFlash footprint
2 KBRAM footprint

— THE CONSTRAINT

A 12-CLASS
NEURAL NET
HAS TO FIT
IN A CALCULATOR.

Indian Sign Language. Ten IMUs (one per finger) over I²C into a NodeMCU, sampled at 60 Hz, windowed to 2 seconds — 7,200 raw values per gesture. Spectral feature extraction compresses to 234.

A progressively narrowing Dense network (128→64→32→16) quantized to INT8, exported via Edge Impulse, fits the NodeMCU’s tight budget. Bluetooth sends the predicted label to a phone for audio output.

  • Custom dataset: 10 participants × 12 classes × 20 repetitions = 2,400 samples.
  • Team learned ISL formally so gestures matched real-world usage.
  • National Top 10 of 70,000 · Samsung Solve for Tomorrow · CNN News18.
NODEMCU10× IMUEDGE IMPULSETFLITE INT8BLUETOOTH3D PRINT
— WANT THE FULL STORY?

LET’S
BUILD.