Apple Patent: Speech Recognition Improvements?

MacRumors · 02:11 AM

Apple has recently been awarded patents for a number (here, here) of microphone/speech recognition patents.

The most descriptive is this patent which was filed in July 2002 entitled "Microphone elements for a computing system". The patent abstract is as follows:

Quote:

An improved speech recognition device is provided. The speech recognition device comprises a display with at least two built in microphones and a speech recognition module electrically connected to the display. The speech recognition module uses an algorithm that may take into account the position of the built in microphone on the display. The display may have a first axis of rotation where the microphones may be placed an equal distance from the first axis of rotation.

The application itself explains the difficulties in filtering out background noise from speech for recognition, and describes a technique with "at least two built in microphones and a speech recognition module electrically connected to the display".

Apple has not publically released any displays that incorporate this technology.

iJon · Mar 2, 2003, 02:03 AM

wow, this will really be awesome. when will apple ever stop amazing us.

iJon

arn · Mar 2, 2003, 02:06 AM

I think it's most interesting because Apple has seemingly left Speech Recognition untouched for some time.

arn

awulf · Mar 2, 2003, 02:07 AM

Wouldn't a rotating Microphone be a bit weird and expensive?

arn · Mar 2, 2003, 02:10 AM

Quote:

Originally posted by awulf
Wouldn't a rotating Microphone be a bit weird and expensive?

the microphones are attached to the display. They are talking about a display which could potentially rotate.

arn

Bateman · Mar 2, 2003, 02:13 AM

i really hope that if Apple is working with speech recognition that they do it well. speech recognition is such a good idea, in theory and on paper, and i have been waiting to see its potential played out, it will be awhile but maybe Apple will be able to pioneer it to the point that it becomes truly acceptable and openly regarded as an element to a revolutionary way to use computers...

It is tough (setting up speech recognition to work seemlessly with its user), I'm sure, from a technical stand-point, and it shows it with how it performs on most Macs. If i were able to talk at a comfortable pace and the speech recog. would be able to keep up with me while showing great accuracy and using reasonable commands for certain tasks, I could see this as a feature that would be able to catch on.

Include this feature with mouse gestures and you have the future generations of OSes. But i'm getting ahead of myself....

I wonder what they are up to???

Kwyjibo · Mar 2, 2003, 02:14 AM

I'm fairly sure that gettign rid of background noise is supposedly the final key to all speech recognition that and getting the computer to interpete the signals right. If anyone can do this right, its apple.

confirmed · Mar 2, 2003, 02:30 AM

i have to say, this makes me think it'd be used in a PDA. mainly the fact that ita primary improvement is on background noise, in your home, thats not so much of a problem. outside, when you want to convert voice to data, good noise cancelling will be very necessary.

the ipod, "reveloutionary" because it was small and hard drive based. 1,000 songs in your pocket! a PDA with voice based data entry.. definitely revolutionary!

yeah, steve said he doesn't like PDAs. but his reason was because he thought entering text with a little stylus was a flawed method. i think i remember a quote where he asked who wants to write entire emails like that. and he's right. when people use their PDAs for email, they keep the emails as short as they can. if you could just enter as you talk, with even better reliability than Graffiti and other stylus based methods, people would, finally, be able to use a PDA to enter massive amounts of text.

anyone agree?

foniks2020 · Mar 2, 2003, 02:39 AM

Quote:

Originally posted by confirmed
yeah, steve said he doesn't like PDAs. but his reason was because he thought entering text with a little stylus was a flawed method. i think i remember a quote where he asked who wants to write entire emails like that. and he's right. when people use their PDAs for email, they keep the emails as short as they can. if you could just enter as you talk, with even better reliability than Graffiti and other stylus based methods, people would, finally, be able to use a PDA to enter massive amounts of text.

anyone agree?

My thoughts exactly as soon as I read the rumor!!!!! This makes sooooo much sense to me. Who does want to write in all their e-mails? In fact who wants to TYPE them all in, especially on a cramped/carpal keyboard?

I'm thinking the perfect mix of a PDA and a PVR (Personal Voice Recorder). Think about journalism or any professional who takes a lot of notes. They use PVRs all the time but then have to manually transcribe all their notes onto their laptops, etc. Steve probably wants this one for himself!

Well here's hoping that it works as well as the hype will expect it to... Apple will have another winner on their hands.

applefan · Mar 2, 2003, 03:10 AM

Quote:

I'm thinking the perfect mix of a PDA and a PVR (Personal Voice Recorder). Think about journalism or any professional who takes a lot of notes. They use PVRs all the time but then have to manually transcribe all their notes onto their laptops, etc. Steve probably wants this one for himself!

I'm thinking of the perfect mix of PDA/cell phone. The problem with current phone/PDAs is size, and small phones that sync with PIMs are to difficult and slow to enter text into notes, calendar and email. Maybe this technology can address those issues with voice recognition.

redAPPLE · Mar 2, 2003, 03:19 AM

is it just me or am i missing the point...

they are talking about the device, and not about the software right?

AmbitiousLemon · Mar 2, 2003, 03:19 AM

Apple has left speech recognition untouched for so long this is very interesting.

Speech recognition technology has been one of the hardest hit areas by Microsoft vaporware tactics. It is nice to see that someone is attempting to bring us out of the MS imposed dark ages.

It is also interesting to me that this is a hardware assisted speech recognition technology.

Mention of including it in a display is also an interesting note.

also for those discussing pda tech read more than just the blurb. the numbered points make it seem pretty clear that apple is think of this as a addition to a conventional computer rather than any sort of handheld device. if you have used speech recoginition on a mac then you know that getting absolute silience is key and is not so easy to achieve in any environment (home, office, or outside). Noise filtering technology does not therefore point to a handheld device.

i am interested in the multilingual properties of mac osx and how speech recognition could tie in with all of this. will it work for all the osx languages installed? even the tonal languages?

would it be tied to cocoa so that programmers could include voice recog easily into their apps?

AmbitiousLemon · Mar 2, 2003, 03:20 AM

Quote:

Originally posted by redAPPLE
is it just me or am i missing the point...

they are talking about the device, and not about the software right?

they are talking about a dual mic display mounted hardware noise reduction ssytem for use in voice recognition systems.

Choppaface · Mar 2, 2003, 03:51 AM

considering the description of the patent for the backlit keyboard, it's going to be very interesting to see what this turns out to be

michaelyoung · Mar 2, 2003, 03:58 AM

For all the wishful thinking about an Apple PDA, I must say, that I just got the t68i and it comes pretty darn close to everything i would hope for. As long as you dont need to input on the go. But I didnt do that much with my old Palm.
With the new form factor (P800?) a real convergent device may finally be here in a reasonable size.
Plus, I'm the kind of geek who will buy anything from Apple but i dont want _another_ thing to clip on to my belt. If Apple _did_ make a phone they would have to make in in GSM and TDMA and all the others. It just seems very complicated.
Sorry i'm tired

Sol · Mar 2, 2003, 04:36 AM

I do not understand why two microphones are necessary for speech recognition. The only theory I have about this is that one microphone would pick up the person speaking and the other would pick up the background noise. Using some type of hardware/software process the background sound would be negated from the speech signal, kind of like the system Bose use in their hi-fi and Sony in their Noise Canceling headphones. This would make the speech more distinct for the computer and improve the speech recognition process.

As for the speech recognition module, I have absolutely no idea what this would be. Maybe the CPU would not be utilized for this application by offloading the work to a hardware module. If this is the case then it could definitely be intended for a portable device but considering Steve Jobs' comments about PDAs it could be a part of something unprecedented.

Nermal · Mar 2, 2003, 05:04 AM

Well it looks like the speech recognition tasks will be done using a dedicated processor. Having used speech recognition software, I find it frustratingly slow, but if it is using a dedicated processor then this should speed it up significantly.

I also can't help but think that the rumoured plastic enclosure (on page 2) has something to do with this - I'm imagining a PDA-style device. But I'm no good at predictions

inkswamp · Mar 2, 2003, 05:12 AM

Quote:

Originally posted by confirmed
i have to say, this makes me think it'd be used in a PDA.
[...]
anyone agree?

OMFG! I rarely read posts on rumors sites that have the feel of being right on target, but your post is. I think you've hit it right on!

I work in a setting with many journalists around me. I could only imagine the stampede a product like that would create amongst journalists, the idea that they could potentially take an iPod-like device, interview someone, make verbal notes and then hook up to their Mac and watch the whole thing pop into their word processor, fully transcribed. Amazing. I watch them sit there with tape recorders, doing the play-pause-rewind-type-repeat method. This would be a killer way to save time and effort.

I can imagine lots of other fantastic uses for this too. I do a lot of recreational writing (fiction, humor, etc.) and I would definitely get this. I don't own a PDA and I don't own an iPod, but this concept would change that immediately. What a great concept. I hope Apple is doing exactly what you posted.

Winston Smith · Mar 2, 2003, 05:13 AM

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!

boskie · Mar 2, 2003, 06:32 AM

Quote:

Originally posted by AmbitiousLemon

i am interested in the multilingual properties of mac osx and how speech recognition could tie in with all of this. will it work for all the osx languages installed? even the tonal languages?

Finally!

A universal translator for speaking to the in-laws!!!

Oh, wait... I'll also find out what they were shouting at my wedding...

newnomad · Mar 2, 2003, 07:42 AM

Using 2 microphones (close to each other) is something that has been done for ages in public address (microphone singers of bands,...) The 2 mics have opposite fases and thus filter out all the background, destroying feedback problems. Its a purely physical thing, no dsp.
I wonder if they also consider pressure zone microphones (PZM)

As for pda's (and all small input devices for digital gizmos for that matter) I think its about time we learn a whole new 1 hand operated way of typing. Man stands above machine and is smart enough to adapt.
If it works for a trumpetplayer......

arn · Mar 2, 2003, 08:31 AM

Quote:

Originally posted by newnomad
As for pda's (and all small input devices for digital gizmos for that matter) I think its about time we learn a whole new 1 hand operated way of typing. Man stands above machine and is smart enough to adapt.
If it works for a trumpetplayer......

This actually does exist. Do a search for chording keyboards. They never caught on...

Here's one:
http://www.handykey.com/

arn

dstorey · Mar 2, 2003, 08:32 AM

I think this parts intresting:

Of course, the computer system may have many physical forms ranging from an integrated circuit, a printed circuit board, and a small handheld device up to a desktop personal computer. Computer system 900 includes a monitor 902, a display 904, a chassis 906, a disk drive 908, a keyboard 910, and a mouse 912. Disk 914 is a computer-readable medium used to transfer data to and from computer system 900. So that the computer system 900 may be an example of the computer system illustrated in FIG. 2, a stand 905 is provided. A hinge 907 allows the monitor 902 to be mounted to the stand 905, so that the monitor may be able to rotate around a display axis 909. A first microphone 911 and a second microphone 913 are set on each side of the monitor 902 on the display axis 909.

Sounds like its not just a pda but mainly for desktop systems. The whole thing talks about a rotating display and this doesn't suggest a pda and i cant work out why or how a pda would have a rotating axis, unless it just means the user manually turning the device, but this doesn't use multiple axis. It sounds more to me like an iMac where the screen can rotate on the neck for whatever reason. And by the sounds of that description, a studio display that has mic's and a display stand so it can rotate and have free movement like the iMac.

What would be reallt intresting is if the display had a cam as well, and could automatically move and rotate to follow the user or turn to face a second speaker when they start talking. very useful for meetings, but very confusing for the poor mac if an argument ensued. The all seeing, all listening, dancing iMac anyone, how much cool factor would that have. Then imagine a touch screen displat, with pressure sensitive stylus, to add diagrams and hand written notes and sig's, bluetooth light up keys, mouse (which has thumb wheel and senses which side you click for two button mouse that looks like one) and possibly 5.1/7.1 wireless speakers for a wire free tidy desktop. These bluetooth deviced would need some way to recharge, as plugging into a cradle gets rid of the wireless advantage as the cradles have wires. some form of kinetic or solar power would be good (no way kinetic would work for speakers though). Now just add IBM PowerPc 970 @ 2.5 GHz and you have an amazing desirable computer. Not very likely i know but how many of you would buy one. Oh the display would have to be removeable so when your mac is old you can buy just the base and use your old display/cam/mic's, mouse and keys.

Add iApps to allow you to watch tv on the iMac (removes the need for a seperate portable in the study/kids room/ wherever the mac is) and allow to record a la tivo. and a iHome app that controls standard devices for home automation systems (possibly over bluetooth/WiFi depending on range). This would allow you to use playlists for the home, such as have settings for the lights, heating etc when your at work/holiday/night time/romantic night in(controlling the dimmer switch

) etc . This would intergrate with iCal so you can see and edit the settings by day/month/year, and .mac so you can control remotely while your at work/holiday. If the display could even turn itself you could have bluetooth movement sensors for the home where if someone moves into the room where the mac is, the sensor transmits to the mac and it turns and starts to record with the cam and saves t your .mac account. Imagine a burgulars face as the mac turns and greets them

. Ok ok it's mostly fantasy and very unlikely but it is technically possible. sorry for going so off topic

Sonofhaig · Mar 2, 2003, 09:45 AM

This post reminds me of the scene in "Star Trek, The Voyage Home". Scottie, talking to a 20th century computer, to use it.

Well, if anyone can bring us closer to that kind of technology........it's Apple.

Freg3000 · Mar 2, 2003, 10:24 AM

Anyone think that this might just be a device to input voice reg. into a video conferencing iChat? I'd like to see a PDA, but, I have my doubts.

Mar 2, 2003, 02:07 AM	#4
awulf macrumors 6502 Join Date: Mar 2002 Location: South Australia	Wouldn't a rotating Microphone be a bit weird and expensive? __________________ Join The MacRumors Folding Team Now! The Mac Specifications Database

Mar 2, 2003, 03:19 AM	#12
AmbitiousLemon Demi-God (Moderator) Join Date: Nov 2001 Location: down in Fraggle Rock	Apple has left speech recognition untouched for so long this is very interesting. Speech recognition technology has been one of the hardest hit areas by Microsoft vaporware tactics. It is nice to see that someone is attempting to bring us out of the MS imposed dark ages. It is also interesting to me that this is a hardware assisted speech recognition technology. Mention of including it in a display is also an interesting note. also for those discussing pda tech read more than just the blurb. the numbered points make it seem pretty clear that apple is think of this as a addition to a conventional computer rather than any sort of handheld device. if you have used speech recoginition on a mac then you know that getting absolute silience is key and is not so easy to achieve in any environment (home, office, or outside). Noise filtering technology does not therefore point to a handheld device. i am interested in the multilingual properties of mac osx and how speech recognition could tie in with all of this. will it work for all the osx languages installed? even the tonal languages? would it be tied to cocoa so that programmers could include voice recog easily into their apps? __________________ Where in the world is Willard now?

Mar 2, 2003, 03:58 AM	#15
michaelyoung macrumors member Join Date: Jun 2002	PDA For all the wishful thinking about an Apple PDA, I must say, that I just got the t68i and it comes pretty darn close to everything i would hope for. As long as you dont need to input on the go. But I didnt do that much with my old Palm. With the new form factor (P800?) a real convergent device may finally be here in a reasonable size. Plus, I'm the kind of geek who will buy anything from Apple but i dont want _another_ thing to clip on to my belt. If Apple _did_ make a phone they would have to make in in GSM and TDMA and all the others. It just seems very complicated. Sorry i'm tired

Mar 2, 2003, 04:36 AM	#16
Sol macrumors 65816 Join Date: Jan 2003 Location: Australia	A few ideas about this I do not understand why two microphones are necessary for speech recognition. The only theory I have about this is that one microphone would pick up the person speaking and the other would pick up the background noise. Using some type of hardware/software process the background sound would be negated from the speech signal, kind of like the system Bose use in their hi-fi and Sony in their Noise Canceling headphones. This would make the speech more distinct for the computer and improve the speech recognition process. As for the speech recognition module, I have absolutely no idea what this would be. Maybe the CPU would not be utilized for this application by offloading the work to a hardware module. If this is the case then it could definitely be intended for a portable device but considering Steve Jobs' comments about PDAs it could be a part of something unprecedented. __________________ DOWN WITH BIG BROTHER

Mar 2, 2003, 05:13 AM	#19
Winston Smith macrumors regular Join Date: Feb 2003 Location: Oceania	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! __________________ Bondi Blue Rev B iMac 1.25 Ghz Rev A Powerbook 15" 1.33Ghz iBook 14" 20" Cinema Display 1.5Ghz Rev C Powerbook 15" (Scratchcard Winner on Tiger night at Regent Street!)

Mar 2, 2003, 02:03 AM	#2
iJon macrumors 601 Join Date: Feb 2002	wow, this will really be awesome. when will apple ever stop amazing us. iJon

Mar 2, 2003, 02:06 AM	#3
arn macrumors god Join Date: Apr 2001	I think it's most interesting because Apple has seemingly left Speech Recognition untouched for some time. arn

Mar 2, 2003, 02:13 AM	#6
Bateman macrumors member Join Date: Jan 2003 Location: TN	i really hope that if Apple is working with speech recognition that they do it well. speech recognition is such a good idea, in theory and on paper, and i have been waiting to see its potential played out, it will be awhile but maybe Apple will be able to pioneer it to the point that it becomes truly acceptable and openly regarded as an element to a revolutionary way to use computers... It is tough (setting up speech recognition to work seemlessly with its user), I'm sure, from a technical stand-point, and it shows it with how it performs on most Macs. If i were able to talk at a comfortable pace and the speech recog. would be able to keep up with me while showing great accuracy and using reasonable commands for certain tasks, I could see this as a feature that would be able to catch on. Include this feature with mouse gestures and you have the future generations of OSes. But i'm getting ahead of myself.... I wonder what they are up to???

Mar 2, 2003, 02:14 AM	#7
Kwyjibo macrumors 68040 Join Date: Nov 2002	I'm fairly sure that gettign rid of background noise is supposedly the final key to all speech recognition that and getting the computer to interpete the signals right. If anyone can do this right, its apple.

Mar 2, 2003, 02:30 AM	#8
confirmed macrumors regular Join Date: Dec 2001 Location: New York, NY	i have to say, this makes me think it'd be used in a PDA. mainly the fact that ita primary improvement is on background noise, in your home, thats not so much of a problem. outside, when you want to convert voice to data, good noise cancelling will be very necessary. the ipod, "reveloutionary" because it was small and hard drive based. 1,000 songs in your pocket! a PDA with voice based data entry.. definitely revolutionary! yeah, steve said he doesn't like PDAs. but his reason was because he thought entering text with a little stylus was a flawed method. i think i remember a quote where he asked who wants to write entire emails like that. and he's right. when people use their PDAs for email, they keep the emails as short as they can. if you could just enter as you talk, with even better reliability than Graffiti and other stylus based methods, people would, finally, be able to use a PDA to enter massive amounts of text. anyone agree?

Mar 2, 2003, 03:19 AM	#11
redAPPLE macrumors 68020 Join Date: May 2002 Location: 2 Much Infinite Loops	is it just me or am i missing the point... they are talking about the device, and not about the software right?

Mar 2, 2003, 03:51 AM	#14
Choppaface macrumors 65816 Join Date: Jan 2002 Location: SFBA	considering the description of the patent for the backlit keyboard, it's going to be very interesting to see what this turns out to be

Mar 2, 2003, 05:04 AM	#17
Nermal Demi-God (Moderator) Join Date: Dec 2002 Location: Whakatane, New Zealand	Well it looks like the speech recognition tasks will be done using a dedicated processor. Having used speech recognition software, I find it frustratingly slow, but if it is using a dedicated processor then this should speed it up significantly. I also can't help but think that the rumoured plastic enclosure (on page 2) has something to do with this - I'm imagining a PDA-style device. But I'm no good at predictions

Mar 2, 2003, 07:42 AM	#21
newnomad macrumors newbie Join Date: Mar 2003	2 microphones Using 2 microphones (close to each other) is something that has been done for ages in public address (microphone singers of bands,...) The 2 mics have opposite fases and thus filter out all the background, destroying feedback problems. Its a purely physical thing, no dsp. I wonder if they also consider pressure zone microphones (PZM) As for pda's (and all small input devices for digital gizmos for that matter) I think its about time we learn a whole new 1 hand operated way of typing. Man stands above machine and is smart enough to adapt. If it works for a trumpetplayer......

Mar 2, 2003, 08:32 AM	#23
dstorey macrumors 6502a Join Date: Dec 2002	I think this parts intresting: Of course, the computer system may have many physical forms ranging from an integrated circuit, a printed circuit board, and a small handheld device up to a desktop personal computer. Computer system 900 includes a monitor 902, a display 904, a chassis 906, a disk drive 908, a keyboard 910, and a mouse 912. Disk 914 is a computer-readable medium used to transfer data to and from computer system 900. So that the computer system 900 may be an example of the computer system illustrated in FIG. 2, a stand 905 is provided. A hinge 907 allows the monitor 902 to be mounted to the stand 905, so that the monitor may be able to rotate around a display axis 909. A first microphone 911 and a second microphone 913 are set on each side of the monitor 902 on the display axis 909. Sounds like its not just a pda but mainly for desktop systems. The whole thing talks about a rotating display and this doesn't suggest a pda and i cant work out why or how a pda would have a rotating axis, unless it just means the user manually turning the device, but this doesn't use multiple axis. It sounds more to me like an iMac where the screen can rotate on the neck for whatever reason. And by the sounds of that description, a studio display that has mic's and a display stand so it can rotate and have free movement like the iMac. What would be reallt intresting is if the display had a cam as well, and could automatically move and rotate to follow the user or turn to face a second speaker when they start talking. very useful for meetings, but very confusing for the poor mac if an argument ensued. The all seeing, all listening, dancing iMac anyone, how much cool factor would that have. Then imagine a touch screen displat, with pressure sensitive stylus, to add diagrams and hand written notes and sig's, bluetooth light up keys, mouse (which has thumb wheel and senses which side you click for two button mouse that looks like one) and possibly 5.1/7.1 wireless speakers for a wire free tidy desktop. These bluetooth deviced would need some way to recharge, as plugging into a cradle gets rid of the wireless advantage as the cradles have wires. some form of kinetic or solar power would be good (no way kinetic would work for speakers though). Now just add IBM PowerPc 970 @ 2.5 GHz and you have an amazing desirable computer. Not very likely i know but how many of you would buy one. Oh the display would have to be removeable so when your mac is old you can buy just the base and use your old display/cam/mic's, mouse and keys. Add iApps to allow you to watch tv on the iMac (removes the need for a seperate portable in the study/kids room/ wherever the mac is) and allow to record a la tivo. and a iHome app that controls standard devices for home automation systems (possibly over bluetooth/WiFi depending on range). This would allow you to use playlists for the home, such as have settings for the lights, heating etc when your at work/holiday/night time/romantic night in(controlling the dimmer switch ) etc . This would intergrate with iCal so you can see and edit the settings by day/month/year, and .mac so you can control remotely while your at work/holiday. If the display could even turn itself you could have bluetooth movement sensors for the home where if someone moves into the room where the mac is, the sensor transmits to the mac and it turns and starts to record with the cam and saves t your .mac account. Imagine a burgulars face as the mac turns and greets them . Ok ok it's mostly fantasy and very unlikely but it is technically possible. sorry for going so off topic

Mar 2, 2003, 09:45 AM	#24
Sonofhaig macrumors regular Join Date: Jan 2003 Location: Greenvale, NY	Reminds me of Scottie... This post reminds me of the scene in "Star Trek, The Voyage Home". Scottie, talking to a 20th century computer, to use it. Well, if anyone can bring us closer to that kind of technology........it's Apple. __________________

Mar 2, 2003, 10:24 AM	#25
Freg3000 macrumors 68000 Join Date: Sep 2002 Location: New York	Anyone think that this might just be a device to input voice reg. into a video conferencing iChat? I'd like to see a PDA, but, I have my doubts. __________________ FregTK This Is Momentum.

Thread Tools	Search this Thread
Show Printable Version Email this Page	Search this Thread: Advanced Search
Display Modes
Linear Mode Switch to Hybrid Mode Switch to Threaded Mode