Hacker News Reader

Comment by briga | Hacker News Reader

Correct, but most neural networks that do this sort of thing have tens of millions of parameters. Doing this in only 150 KB is extremely memory-efficient, if not exactly high fidelity.

View on HN

You are absolutely right. Compressing (using this for lack of better terminology) is extremely important for power-efficient applications as one of the main power draws on a device is external RAM.

We had to come up with a bunch of ideas on how to fit our stack into the on-chip RAM (512 KB) and leave enough for OS and the actual application.

Do you have some details on how you have done this?

Yes, we will publish an article about our speech-to-intent engine and add a link to it on our website. This should happen before the new year.

You can find some information about the wake-word engine here https://medium.com/@alirezakenarsarianhari/yet-another-wake-...

This is excellent work. Is there a catch? Limited vocabulary versus open domain? Noise or accent sensitive? How large is the model file? What's the accuracy? It's amazing you were able to get anything beyond keyword spotting on such a relatively low power computer.

Thank you. The engine is definitely domain-specific. This would apply to vocabulary and also inference. For example, if you want to use the tech for smart lighting then you would need a different model/context.

The demo is done with some noise and there is some reverberation as well. The speakers are also somewhat accented. That being said we would like to open-source a benchmark for this (similar to other products we have). The comment on accuracy is a bit tricky as it would depend on parameters you mentioned and specific task. I will provide more information when we open source the benchmark in Q1 2019.

Reply on news.ycombinator.com