Google Assistant will use more than one device to decipher the voice commands | Hacker News Reader

Google Assistant will use more than one device to decipher the voice commands

whatafuture.com

tl;dr

- this is not a Google announcement but a Google patent. Not sure if this will be implemented

- the idea would be to use two devices at same time to improve Google Assistant's understanding of voice commands (reduce transcription mistakes, "hear" the difference between "of" and "off" etc...)

Still quite interesting if it becomes a reality.

Let's see what other thinks.

Can we update the title to the article's actual title? It is currently quite misleading.

"Google Assistant will use more than one device to decipher the exact voice commands"

Sorry guys, I am unable to change that title.

Thanks, we've updated the title from “Google Assistant now can use two devices at same time for a voice command”.

I think siri already has this feature. I am not sure but Siri can differentiate the devices without telling about a device.

Can you give me example. I never noticed this but then again, I haven't used Siri as much.

If I have my iPad and iPhone in front of me, both with "Hey Siri" activation turned on, both will register that I asked. But only one of them will respond 'verbally'.

I'm not sure if that's what the OP meant, though.

Oh yes, that could be a case. Pretty impressive though.

This already exists for Google Assistant devices, but is not what the article is talking about.

The article implies that it will fuse voice data from multiple devices which both only heard part of the query into a single query, which is a lot easier to write down in a patent than to actually make work.

Title is misleading. This isn't a new feature of Google Assistant; just a patent. The actual article title is a bit better, but still implies this is a feature we'll be seeing in the near future, which isn't necessarily the case.

This has happened previously as well that Google implemented a feature much before filing a patent for it. Google is not a company that waste their money on filing patents that they'll never implement.

I thought mentioning that it is a patent will have little or no effect on whether this feature comes to reality or not.

Edit: Original article title: "Google Assistant will use more than one device to decipher the exact voice commands"

> Edit: Original article title: "Google Assistant will use more than one device to decipher the exact voice commands"

FYI, that's _still_ the article title; it hasn't changed. The HN post title is currently "Google Assistant now can use two devices at same time for a voice command", which is even more misleading to the point of being just flat-out wrong.

>This has happened previously as well that Google implemented a feature much before filing a patent for it. //

If the feature were "published" it would serve as prior art and invalidate the patent.

The patent tells about the new feature of Google assistant. And most of the time Google implement the technologies.

I wish there was simply a wall plug I could put in another room that connected to the main Home unit. So if I'm in a different room yada yada...

nVidia announced one of those.

http://www.pocket-lint.com/review/139949-nvidia-spot-preview...

(But works with Shield, not Home, it seems?)

But it was never released with no news about when it is coming out.

Reply on news.ycombinator.com