TinyDenoiser: RNN-based Speech Enhancement on Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization

TinyDenoiser: RNN-based Speech Enhancement on Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization

EDGE AI FOUNDATION via YouTube Direct link

RNN Mapping on HW

5 of 9

5 of 9

RNN Mapping on HW

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

TinyDenoiser: RNN-based Speech Enhancement on Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Speech Enhancement (or Denoising)
  3. 3 RNN for Speech Enhancement
  4. 4 RISC-V MultiCore MCU Platform (GAP9)
  5. 5 RNN Mapping on HW
  6. 6 Optimizations: Double Buffering
  7. 7 Optimizations: Tensor Promotion
  8. 8 Post-Training Quantization
  9. 9 Latency & Power on target HW/SW

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.