By using this site, you agree to our Privacy Policy and our Terms of Use. Close

Forums - Nintendo - A Golden Wii U Opportunity

Busted on 04 January 2013
Mazty said:
Busted said:
Mazty said:

No chance. You guys may as well be saying "will the next xbox run on magic and sprinkes?". What you are suggesting is far, far too complex for a relatively weak console to be doing, and even for a top of the range $5000 PC.

Really?

Yep. There's a good reason voice recognition is based from servers rather then local systems. When you have to account for sentence structure, accent, pitch etc there are a lot of variables, and that's just to understand what has been said. A good example is that Watson, the supercomputer that was used in Jepoardy, didn't actually translate the questions - it had them digitally sent at the same time as when the question was asked. 

I wasn't talking about that... but ok, you gave me all i needed.



Around the Network
timmah on 04 January 2013
Mazty said:
NintendoPie said:
Mazty said:
NintendoPie said:

Not exactly. I'm pretty sure games/gaming consoles are able to remember fights and progression in story lines. Even the DS can do this. The Wii U could most likely handle something like this very easily. 

Besides, the Wii U isn't a "relatively weak" console.


If voice recognition is so simple then why does Siri run off of a server farm?
And yes the wii u is relatively weak compared to say an i5 3770k. 

So what if Siri uses a server farm? Many things use voice recognition other than Siri. I doubt it's that hard.

*smh*
Do you have any technical knowledge of voice recognition? It is incredibly difficult. Please don't just guess at things. 

Um, this whole debate is pointless since voice recognition is not a good description of Siri, only a small part. Siri is a conversational search engine that utilizes voice recognition. All of the behind the scenes 'magic' that happens after the voice is recognized is what's hard, voice recognition has been around a long time. So no, a natural conversation as described in the 3rd post on page 1 is not possible if only processed on the Wii U (or any other inexpensive hardware), but more limited things that are still neat could be done. On the other hand, if it utilized a cloud based system similar to Siri, it could theoretically be done.



Mazty on 04 January 2013
timmah said:
Mazty said:
timmah said:
Mazty said:
Busted said:
Mazty said:

No chance. You guys may as well be saying "will the next xbox run on magic and sprinkes?". What you are suggesting is far, far too complex for a relatively weak console to be doing, and even for a top of the range $5000 PC.

Really?

Yep. There's a good reason voice recognition is based from servers rather then local systems. When you have to account for sentence structure, accent, pitch etc there are a lot of variables, and that's just to understand what has been said. A good example is that Watson, the supercomputer that was used in Jepoardy, didn't actually translate the questions - it had them digitally sent at the same time as when the question was asked. 

Processor requirements for Dragon Naturally Speaking:

CPU: We recommend 2.2 GHz Intel® dual core or equivalent AMD processor. (Minimum 1 GHz Intel® Pentium® or equivalent AMD processor or 1.66 GHz Intel® Atom® processor). NOTE: Faster processors yield faster performance. (IMPORTANT: SSE2 instruction set is required)

Voice Recognition does not require a ton of processing. It's the AI algorithms that happen after the voice recognition to come up with the response that require a bit of processing. I'm sure a game could utilize cloud-based processing to make something like this happen, but most likely won't. The best we could hope for is pre-programmed voice commands with canned responses, though a lot of cool stuff could still be done with that given enough developer effort.

Is it replying to you? Nope. Voice-to-text is one thing, having a 2 way conversation is another. As you said the voice recognition would just be akin to SOCOM from the PS2 with pre-programmed voice commands. 

It could reply to you. Voice to text, game then knows to extract certain key words from text, searches database of responses, respondes as needed. Not as good as siri, but could be used to enhance a game, since the responses to the situations in a game are far fewer than those Siri needs to think about. It could still be pretty cool.

EDIT: An application could be in an Iron Man game for example. At any time you could tap a button and say something like "Jarvis, let's upgrade my suit". The game translates this to text (doesn't require much processing), knows to look for pre-programmed key words (in this case 'Jarvis' to know which bank of responses to search, then 'upgrade' and 'suit' to know what response to present), Jarvis' voice comes through the gamepad "I've prepared a list of available suit upgrades for you, sir", and that menu pops up on the touch screen with upgrades for suit armor and flight capabilities. If you said "Jarvis, I really need to upgrade my weapons", it would extract Jarvis, upgrade, weapons and similarly present you with the weapon upgrade screen. This is a set of searches based on only 3 key words (not a lot of processing to do a keyword search) to get a really cool effect. It would be limited in scope, IE, not full, natural conversation, but could be done to a certain degree.


If we run off the voice-to-text software, that's using a dual core 2.2ghz to just write it down. To analyse the sentence as well would be too taxing on the Wii U. It could be done, but I'm doubtful that it could be done in a reasonable amount of time on the wii u as in you don't want a 10 second pause after every command. 



Mazty on 04 January 2013
timmah said:
Mazty said:
NintendoPie said:
Mazty said:
NintendoPie said:

Not exactly. I'm pretty sure games/gaming consoles are able to remember fights and progression in story lines. Even the DS can do this. The Wii U could most likely handle something like this very easily. 

Besides, the Wii U isn't a "relatively weak" console.


If voice recognition is so simple then why does Siri run off of a server farm?
And yes the wii u is relatively weak compared to say an i5 3770k. 

So what if Siri uses a server farm? Many things use voice recognition other than Siri. I doubt it's that hard.

*smh*
Do you have any technical knowledge of voice recognition? It is incredibly difficult. Please don't just guess at things. 

Um, this whole debate is pointless since voice recognition is not a good description of Siri, only a small part. Siri is a conversational search engine that utilizes voice recognition. All of the behind the scenes 'magic' that happens after the voice is recognized is what's hard, voice recognition has been around a long time. So no, a natural conversation as described in the 3rd post on page 1 is not possible if only processed on the Wii U (or any other inexpensive hardware), but more limited things that are still neat could be done. On the other hand, if it utilized a cloud based system similar to Siri, it could theoretically be done.

I guess I should have been saying speech recognition, as in understanding the sentence structure at the same time instead of just recognising a voice. Still, it's not a fast process.
Using a cloud system is very viable but costly. Maybe if a company made the cloud system for multiple games to use that is when it could financially become viable. 



timmah on 04 January 2013
Mazty said:
timmah said:
Mazty said:
timmah said:
Mazty said:
Busted said:
Mazty said:

No chance. You guys may as well be saying "will the next xbox run on magic and sprinkes?". What you are suggesting is far, far too complex for a relatively weak console to be doing, and even for a top of the range $5000 PC.

Really?

Yep. There's a good reason voice recognition is based from servers rather then local systems. When you have to account for sentence structure, accent, pitch etc there are a lot of variables, and that's just to understand what has been said. A good example is that Watson, the supercomputer that was used in Jepoardy, didn't actually translate the questions - it had them digitally sent at the same time as when the question was asked. 

Processor requirements for Dragon Naturally Speaking:

CPU: We recommend 2.2 GHz Intel® dual core or equivalent AMD processor. (Minimum 1 GHz Intel® Pentium® or equivalent AMD processor or 1.66 GHz Intel® Atom® processor). NOTE: Faster processors yield faster performance. (IMPORTANT: SSE2 instruction set is required)

Voice Recognition does not require a ton of processing. It's the AI algorithms that happen after the voice recognition to come up with the response that require a bit of processing. I'm sure a game could utilize cloud-based processing to make something like this happen, but most likely won't. The best we could hope for is pre-programmed voice commands with canned responses, though a lot of cool stuff could still be done with that given enough developer effort.

Is it replying to you? Nope. Voice-to-text is one thing, having a 2 way conversation is another. As you said the voice recognition would just be akin to SOCOM from the PS2 with pre-programmed voice commands. 

It could reply to you. Voice to text, game then knows to extract certain key words from text, searches database of responses, respondes as needed. Not as good as siri, but could be used to enhance a game, since the responses to the situations in a game are far fewer than those Siri needs to think about. It could still be pretty cool.

EDIT: An application could be in an Iron Man game for example. At any time you could tap a button and say something like "Jarvis, let's upgrade my suit". The game translates this to text (doesn't require much processing), knows to look for pre-programmed key words (in this case 'Jarvis' to know which bank of responses to search, then 'upgrade' and 'suit' to know what response to present), Jarvis' voice comes through the gamepad "I've prepared a list of available suit upgrades for you, sir", and that menu pops up on the touch screen with upgrades for suit armor and flight capabilities. If you said "Jarvis, I really need to upgrade my weapons", it would extract Jarvis, upgrade, weapons and similarly present you with the weapon upgrade screen. This is a set of searches based on only 3 key words (not a lot of processing to do a keyword search) to get a really cool effect. It would be limited in scope, IE, not full, natural conversation, but could be done to a certain degree.


If we run off the voice-to-text software, that's using a dual core 2.2ghz to just write it down. To analyse the sentence as well would be too taxing on the Wii U. It could be done, but I'm doubtful that it could be done in a reasonable amount of time on the wii u as in you don't want a 10 second pause after every command. 

That's the recommended, it can run on as little as an Atom (which is a terrible processor). Also keep in mind that we're talking about a PC which is running a full OS and a bunch of other threads in the background. I've used Dragon on an old Intel Dual Core at 1.6GHz and it didn't eat up much of my processor to use it, so it's definitely not terribly taxing.



Around the Network
the_dengle on 04 January 2013

Portal 3.



timmah on 04 January 2013
Mazty said:
timmah said:
Mazty said:
NintendoPie said:
Mazty said:
NintendoPie said:

Not exactly. I'm pretty sure games/gaming consoles are able to remember fights and progression in story lines. Even the DS can do this. The Wii U could most likely handle something like this very easily. 

Besides, the Wii U isn't a "relatively weak" console.


If voice recognition is so simple then why does Siri run off of a server farm?
And yes the wii u is relatively weak compared to say an i5 3770k. 

So what if Siri uses a server farm? Many things use voice recognition other than Siri. I doubt it's that hard.

*smh*
Do you have any technical knowledge of voice recognition? It is incredibly difficult. Please don't just guess at things. 

Um, this whole debate is pointless since voice recognition is not a good description of Siri, only a small part. Siri is a conversational search engine that utilizes voice recognition. All of the behind the scenes 'magic' that happens after the voice is recognized is what's hard, voice recognition has been around a long time. So no, a natural conversation as described in the 3rd post on page 1 is not possible if only processed on the Wii U (or any other inexpensive hardware), but more limited things that are still neat could be done. On the other hand, if it utilized a cloud based system similar to Siri, it could theoretically be done.

I guess I should have been saying speech recognition, as in understanding the sentence structure at the same time instead of just recognising a voice. Still, it's not a fast process.
Using a cloud system is very viable but costly. Maybe if a company made the cloud system for multiple games to use that is when it could financially become viable. 

Agreed. What I'm talking about is not understanding structure, but picking out 2-3 key words and playing a pre-recorded response based on that. Much, much simpler than full conversation but could work well in some games. "Where would you like to go, sir?" "Take me back to the damn bat cave". The system only has to pick out the phrase 'bat cave' or whatever other destination there might be, then play back one of several pre-recorded responses and execute the command.

Edit: Also, since it's a game, the voice commands could be contextual, meaning there may not be many responses needed for a given situation (especially if the gamepad is asking you a question). "Which weapon would you like to upgrade?" only has a finite number of keywords in responses.



Mazty on 04 January 2013
timmah said:
Mazty said:

If we run off the voice-to-text software, that's using a dual core 2.2ghz to just write it down. To analyse the sentence as well would be too taxing on the Wii U. It could be done, but I'm doubtful that it could be done in a reasonable amount of time on the wii u as in you don't want a 10 second pause after every command. 

That's the recommended, it can run on as little as an Atom (which is a terrible processor). Also keep in mind that we're talking about a PC which is running a full OS and a bunch of other threads in the background. I've used Dragon on an old Intel Dual Core at 1.6GHz and it didn't eat up much of my processor to use it, so it's definitely not terribly taxing.

But when you're running a game in the background...That's when it'd get problematic unless it was done in post-action moments e.g. at the end of missions. 



timmah on 04 January 2013
Mazty said:
timmah said:
Mazty said:

If we run off the voice-to-text software, that's using a dual core 2.2ghz to just write it down. To analyse the sentence as well would be too taxing on the Wii U. It could be done, but I'm doubtful that it could be done in a reasonable amount of time on the wii u as in you don't want a 10 second pause after every command. 

That's the recommended, it can run on as little as an Atom (which is a terrible processor). Also keep in mind that we're talking about a PC which is running a full OS and a bunch of other threads in the background. I've used Dragon on an old Intel Dual Core at 1.6GHz and it didn't eat up much of my processor to use it, so it's definitely not terribly taxing.

But when you're running a game in the background...That's when it'd get problematic unless it was done in post-action moments e.g. at the end of missions. 

Due to the fact that background noise would interfere, I'd imagine the game would have to pause for a second while listening for the response anyway, so not an issue since you couldn't even consider doing voice commands during a loud, cpu-intense action sequence. It would definitely be limited if not running off a cloud-based system.



OceanJ on 04 January 2013

Hey you guys are getting into the nuts and bolts of the possibility, that's awesome. Well, I'm not a tech-guy and have no idea if it's possible on the Wii U.

I'm just an idea guy and all I know is - if the the GamePad were Jarvis...even a weak Jarvis like one who didn't recognize your voice but only controller input responses...like, left-trigger is 'yes' right-trigger for 'no', or, touch the screen to select your answer - I think it could still be a really big hit.

No matter what the Wii U is capable of, I now want a GamePad that is Jarvis, and it seems a logical progression for controls.

At this stage of gaming, we've got all the buttons, we've got the gyroscopes & motion, we've got the touch-screen...what's left? Only one thing. Sound control..voice. Jarvis is all that's left.

That means it will happen. Just a matter of time and the race is now on.