ML-TN-006 — Keyword Spotting and Asymmetric Multiprocessing on Orca SBC

From DAVE Developer's Wiki
Revision as of 16:19, 6 December 2021 by U0001 (talk | contribs) (Created page with "{{InfoBoxTop}} {{AppliesToMachineLearning}} {{AppliesTo Machine Learning TN}} {{AppliesTo ORCA TN}} {{AppliesTo ORCA SBC TN}} {{InfoBoxBottom}} __FORCETOC__ = History = {| c...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
Info Box
NeuralNetwork.png Applies to Machine Learning

History[edit | edit source]

Version Date Notes
1.0.0 December 2021 First public release

Introduction[edit | edit source]

This Technical Note (TN) describes a demo application used to show the combination of an inference algorithm (keyword spotting) and an asymmetric multiprocessing configuration (AMP). This use case can serve as the basis for more complex applications that have to carry out the following tasks:

  • Acquiring data from sensors in real-time
  • Perform a non-trivial inference algorithm on the collected data.

In such a scenario, the power and the flexibility of the NXP i.MX8M Plus can be of much help, as this SoC features a heterogeneous architecture and a Neural Processing Unit (NPU). The idea is to use

Testbed[edit | edit source]

Implementation[edit | edit source]

Testing[edit | edit source]