Apple Patent: Speech Recognition Improvements?

[pncc]

I think the point of multiple mics on a rotating surface is to "tune" the microphone to the user's position for best noise cancellation effectiveness.

I also think a combination of voice and pen input would be a truly practical method of computer input. This could definitely be done with a tablet.

I think this is being positioned for a tablet.

 

[GeneR]

I agree.

Originally posted by Phil Of Mac
Uh, most people.

Keyboards are a fast and efficient way of inputting text. Assuming they could perfect voice recognition, how can you edit and punctuate with voice commands with nearly as much ease as you can type? I'm sure many people don't like to type, but I can't imagine why. I probably have the world's worst motor skills (not counting those with neurological disorders) but I can still type with ease. Especially on my Dvorak keyboard. I can at least type better than I can speak out loud. Certainly you can speak faster than you can type, but typing has many advantages to speech recognition. Anyone who thinks keyboards will fall into disuse is probably wrong.

I agree.

Although I have long believed that voice recognition is the way to go for PDAs like a new version of the iPod that would allow you to record your voice/notes/dictations. If a PDA had a great VR software we'd be all pretty excited (I think). However, we will just have to wait and see if this ever happens.

 

[dongmin]

please don't let this degenerate into another iPDA thread

Originally posted by GeneR
I agree.

Although I have long believed that voice recognition is the way to go for PDAs like a new version of the iPod that would allow you to record your voice/notes/dictations. If a PDA had a great VR software we'd be all pretty excited (I think). However, we will just have to wait and see if this ever happens.

As much as I like the idea of iPod doing voice recognition as an input method, I don't think this particular patent applies to the iPod, PDAs, or any other device that small.

The technology described in the patent clearly requires a minimum of two microphones. There would be no point to putting two microphones on the ipod display because it's so small. Whether this technology is for filtering noise or for locating the sound source, the mics would have to be some distance apart to be effective, like the 17" iMac for example.

 

[GeneR]

Oops. Sorry!

Sorry, I thought this thread included PDAs and iPods.

 

[Phil Of Mac]

Re: Re: Re: Re: Rotating display?

Originally posted by foniks2020
Meta words are better than spelling it out. Say a meta word like 'punctuate' then 'comma'. The software takes 'punctuate' as a queue to listen for 'comma' 'period' 'question' or any of the other marks. If you say something else it assumes you want it to record the word 'punctuate' instead. This is used successfully in other applications like in using mouse gestures where a click-hold-gesture opportunity lasts for a pre-determined amount of time (5 secs is default) then becomes a normal click-hold.

WHAT IF YOU WANT TO WRITE THE WORD "PUNCTUATE"!? That's NINE letters! "COMMA" is FIVE letters! YOU JUST LOST FOUR LETTERS THERE!!!!


AUUUUUUUGHHHH!!!!!!!!!! STOPPP IT NOWWWWWWW!!!!!!!

KHAAAAAAAAAAAAAAN!!!!!

 

[AllenPSU]

Sounds a lot like phase tuning. Wonder how much CPU power its going to take.

 

[mondo]

Originally posted by Winston Smith
Rather than concentrate on it being used for a cool new device, surely this sort of technology fits with everything Apple makes.
How long have PC's totally depended on the GUI as the main point of difference; M$ is stuffed when you wake up and say " open safari, goto Macrumors.com" while your making your first cup of coffee!

I just did this a few minutes ago using ViaVoice. "Open Safari" then "Jump to MacSurfer" and "scroll down" when I'd read the screen. It really was that easy and I'm dictating this message right now.

By the way, what someone else said about Apple not having done anything with voice recognition for some time isn't quite true. They've added a "Front window" feature that allows you to speak any command available where ever you are. There is a visible listing that changes dynamically as you move from place to place.

it's too bad that ViaVoice and Apple's voice-recognition still can't be used simultaneously because of problems with microphone arbitration. Put the two together and you have complete control over the computer by voice.

 

[wrylachlan]

stereo recording iPod?

Could this technology be used to make a really usefull dictation engine for an iPod? My thought is an iPod with two tiny microphones, one in each of the upper corners. It takes dictation in stereo, and when you plug it into your Mac it turns it into text with much better accuracy than single mic recorders... thoughts?

 

[GeneR]

Re: stereo recording iPod?

[i/]Or

 

[GeneR]

Re: stereo recording iPod?

Could this technology be used to make a really usefull dictation engine for an iPod? My thought is an iPod with two tiny microphones, one in each of the upper corners. It takes dictation in stereo, and when you plug it into your Mac it turns it into text with much better accuracy than single mic recorders... thoughts?

I think a few people (myself included) have mentioned this idea but I don't think it was well received by the larger community on this site. I think a lot of people thought it was unrealistic and unreliable due to the current state of voice recognition software today. However, I sure hope they do this. I think it is the really best alternative to having a keyboard attachment, or one of those short hand techniques which still requires your undivided attention as you scribble into your PDA. But that's my thoughts. I guess "great" minds think alike!