[Noisebridge-discuss] Fwd: What to do with these features?

Adam Munich adam at aperture.systems
Sun Apr 12 07:19:29 UTC 2015


I'm trying to reverse engineer the "OK google" functionality implemented in
my phone.


​
What do you suppose I do with those feature / data sets? Since "OK google"
responds to my voice independently of the rate of speech, methinks they are
using a combination of regression analysis and discrete time warping.

But, it's seemingly both speaker and pitch independent too, so there must
be something else going on. There's no way they implemented a full Hidden
Markov Model inside the phone's DSP, (it wouldn't make sense for just one
hotword).

Thoughts?



---
Aperture Systems: Redefining Radiography -  http://aperture.systems/
http://adammunich.com/ - Cell: +1-650-452-0554

Be • knowledgeable •  social • patient • fearless • compassionate • fun •
humble • forgiving.

Be a leader
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.noisebridge.net/pipermail/noisebridge-discuss/attachments/20150412/17970902/attachment-0002.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Capture.PNG
Type: image/png
Size: 147624 bytes
Desc: not available
URL: <http://www.noisebridge.net/pipermail/noisebridge-discuss/attachments/20150412/17970902/attachment-0002.png>


More information about the Noisebridge-discuss mailing list