Slashdot Mirror
Using PDAs for Dictation?
SunPin asks: "I'm a writer that is 99% dependent, due to fine-motor disabilities, on voice dictation. I've been a dictation user since 1990. My preference is 'discrete' speech because of very low resource consumption and its effectively infinite flexibility. Over the years, my computer use has de-evolved to programming, FTP, email (Mozilla), word processing (OpenOffice) and Ricochet. Drop the game and there's nothing that I shouldn't be allowed to do on the go. The problem is that I can't. Back in 1990, the requirements for IBM VoiceType were: DOS, 8MB RAM, 10MB of drive space with one of those new-fangled scorching 386-16MHz processors... not exactly demanding by today's standards and, unless I'm outright wrong, not demanding by today's PDA standards. Why hasn't it occurred yet?"
"In the disability offices of the hundreds of universities across the US, such software would be a major money saver because not all students need a high-powered laptop. While natural speech is great from a marketing perspective, it is simply impractical for general use and cannot adapt to mildly noisy environments. IBM, L & H and Microsoft have all given me the run-around. IBM refused to entertain the possibility. L & H is on life support, in a deep coma. Only Microsoft had a remotely positive response saying that they were testing natural recognition in Mandarin Chinese in their Beijing research office. Does anyone believe in keeping it simple, anymore?"
The reason for this can be put down to a couple of reasons.
First off, buying a dictaphone is still much cheaper than a PDA with software.
And secondly the whole voice/word recognition program market hasn't really accomplished any great leaps or bounds over the past five years, not to mention it's not popular in the mainstream yet.
Be you Admins? nay, we are but lusers!
http://slashdot.org/article.pl?sid=02/11/19/234216 &mode=thread&tid=100
Next thing, you'll be wanting a machine to wash your dishes and clothing, or, heck, let's be crazy, and send moving pictures around the world!
I think it has more to do with the perception of voice dication as unreliable and resource intensive rather than any actual fact, as the poster points out, it can be done fairly cheaply.
I have not had much experience, but I think the other thing is that people are averse to any sort of training or teaching required, no matter the long term dividents.
Like most things, it comes down not to fact, but to perception and prejuidice. Most people base their buying decisions on 30-second spots, not informed research, so the cost of educating people to is too high for producers to incur.
It's the other, most overlooked piece of hardware used in speech recognition, the microphone. The junky headset given away with ViaVoice or the el cheapo unit sold in Radio Shack for under $10 makes most people's experiences with voice recognition software less than favorable. Invest in a $50-$60 professional headset and the ability of the software to accurately detect your speech patterns improves dramatically. How are they going to shoe horn a high fidelity audio sound processor in there? Maybe a USB headset might be the answer assuming the device can accept USB devices.
I'm also going to assume that the current line of speech recognition products are MUCH better than what ran on your old 386.
IBM can't even manage to do this on, for example, a P3 733EB. How they're going to do it on a 300MHz XScale or SH chip or similar (let alone a Motorola Dragonball) is beyond me. I think your head is in the clouds.
With that said, voice recognition is very much on everyone's minds and it is coming. The limiting factor in handhelds right now is battery technology, which seems to be advancing more rapidly now than it has been in the last decade or so. With more power density comes faster processors and more ram, and the ability to perform these kinds of operations on smaller computers.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
To be grammatically correct, a real writer would say, "I'm a writer who....," not "I'm a writer that..." :-)
Yes, we all know that. Nobody has denied this. But for those of us who can't use a keyboard, we're discussing alternatives. Did your bonobo brain fail to grasp that?
Dragon has a portable product that you dock to your PC to do the voice to text. You can bring it with you, then connect it when you're home. A digital recorder is available bundled with the software, or you can use any micro cassett recorder and a Norcom playback and interface device. Seach Google for info!
what kind of machine does Stephan Hawking use nowadays? Last I heard him in early 90's, he was still using 80286 based machine. Today's PDAs running at 400 MHz, 32 bit, should atleast be 50 times faster.
I'm guessing the storage space requirements for that in terms of the data files the programs would use to map vocalizations to meaning would be the biggest stumbling block... Most mainstream PDAs only have 8mb of ram/storage combined, and Palm is still shipping devices with as little as 2mb. Your best bet might be one of the StrongArm based handhelds combined with a reasonably large CompactFlash/SecureDigital card... (E.g. Sharp Zaurus, Hewlett-ComPackard's iPaq, etc.) Of course, that's probably 300-500, but that's still less than a new laptop...
News for Geeks in Austin, TX
With a simple search for dictaphone I was able to find a product called EXSpeech. I think this is what you are looking for.
I think the real reason why the PDA doesnt take voice reconision like the 386 did is bascily the fact that the consumer market who is using the PDAs are use to PC level of quality and when they have voice reconision they want it to work just as good or better then what they have today. So if they made a PDA with 386 level of voice reconision which will get the job done. They will feel that they got riped off.
There is a second possible reason. Sience there is a large drop in the cost of hardware compared to software. That in order for the PDA dealers to seel their equiptment at a market barable price they need to save money on the software side. So Voice Reconision would be a larger undertaking in software side and the extra time to optimize it for the smaller power hardware will cost more. so your $200 PDA could be $300 which would loose some market share for the extra price in a feature that may not work.
There is a third possible reason. Once they make this device the universe will drasticly change into something different.
There is also a forth reason. That this has already happends. (My apoligies to the Late Douglas Adams)
If something is so important that you feel the need to post it on the internet... It probably isn't that important.
Can you imagine how bad it would be if everyone switched to voice recognition? Cellphones are bad enough, imagine if everyone was talking to their computers. The noise would be terrible. No matter how quiet you are, the noise would still grow rather large. Would you want to dictate something to your computer that is supposed to be private? Not when anyone can hear it. I'm waiting for something better, whatever it might be.
Is the poster just dissatisified with existing software: or pissed because he wants to be computing star Trek style and never will?
Unfortunately, the keyboard is the most accurate way to input data.
According to my boss, it's actually something called an office administrator.
My sig sucks.
Unfortunately, the keyboard is the most accurate way to input data.
And more unfortunately, people who can't use them are stuck with voice... or maybe you missed that central theme of this article? What bong-sucking crack-head modded this moron up?
I wonder where your claim that it doesn't work comes from. I have some experience (a couple of hours) with Philips FreeSpeech 2000 (I guess it's called that - I don't have it at hand). It recognizes natural speech fairly accurately. My guess would be that discrete speech is easier to recognize, making for better results and requiring less hardware real estate. I am absolutely willing to bet that it works a lot better than typing for people with disabilities. Your turn again.
Please correct me if I got my facts wrong.
Sorry no links....
There are dictation services availiable on the net, basically you e-mail them an MP3 and they e-mail back a fully typed document.
As far as the reason for voice recognition not being on a PDA, I think it's space requirements. Of the two packages i've tried (dragon dictate and IBM) both of them require a lot of disk space to contain the recognition engine and your personal voice pattern files. Much more than your average PDA can hold. We're probably only a few years off from PDA's having that type of storage.
I recently downloaded Microsoft Reader along with a text to speech add-in and it sounded horrible. Same thing with Adobe's eBook Reader (well, their's was a little better).
But why is this so? Why is text to speech even difficult? If you just have a human person speak all the different phonetic sounds shouldn't it be a simple matter of stringing together those sounds in a relatively seemless way?
The question was "why has this not happened yet". Using the stylus (ala Graffiti) will get the job done, but there is an accuracy problem, which is why keyboards are popular.
Yes, there is software out there that will get the job done I suppose, but because it is not too accurate, it never caught on with the public.
And since there is not a solid ROI, it has not happened. Someone would have to port something for moral reasons....
Conjecture: Voice recognition on a PDA could work if you had a separate voice server over a wireless connection. So you have voice sent over a regular phone connection to you home pc (with modem) that does the recognition, it then spits back text (over another connnection?) to your PDA.
Some might say that this would make VR to slow. I don't see why this would be noticibly slower than doing VR in person. After all, when we talk on the phone the person on the other end hears us almost instananeously.
On a side note: my brother is doctor who uses VR to do his dictations. It is much cheaper than paying a transcription service. He also does not need to review the transcriptions afterwards for accuracy, because he essentially reviews it as he speaks it.
I don't think so.
He is correct, current markets go for the majority and don't bother for the minority (excepting small speciality groups).
Unless you show one of the big players how to turn it in to a cash cow, they won't put to much time or money in to it.
Maybe as a middle ground this could be a good use for a Tablet PC, particularly since it would give you a bigger screen and interface for seeing and marking the text as it is input
just an idea.. it's a handheld Linux based system, so why would this be such a bad idea? hell, while your at it, install festival, so it can talk back
yes yes, a scripting nightmare.. perhaps some enterprising programmers could start something on sourceforge or something..
its not like the technology isn't out there. It's certainly not perfect; the Zarus isn't big on storage space, and it's hardly cheap. and of course countless threads on the imperfection of voice recog.. blah blah.. but good enough is a fine answer on the path to [unattainable] perfection.
Anyway; Keep It Simple, Stupid:
Zarus + Microdrive + ViaVoice/Dragon libs [+ festival?] + glueware = handheld voice recognition..
what's the big deal?
US$0.02++
All you people are talking about speech to text (and a few confused people are talking about text to speech,) but what about just recording audio on these pdas? Even with the storage limitations of most pdas you can still fit several hours of low bitrate and mono audio very easily. Do many pda's have speakers and mikes built in? If so this should be a fairly simple project.
to use PDAs for World Dictation!
MARCH ON MY PALM MINIONS! Go forth! And ravage the world!
*cackles deviously*
The World's Worst Webcomic!
Am I wrong or he just wants an dictation software (versus Speech Recognition) ???
You can get a version of ViaVoice for the PocketPC. However, it sucks. It's not a real dictation system though- it only allows you do use a pretty small pre-defined group of commands, not general english word dictation. I was pretty disapointed. However, I wouldn't be surprised if eventually there will be a full-blown ViaVoice Embedded version for the PocketPC.
As usual, there are some results that come up with a simple Google search.
There was a Dragon Naturally Speaking beta for the Newton OS 2.1, and it works OK. But it's still a beta and is far from perfect.
If you're looking for voice recognition for other PDAs, including PalmOS or Linux devices, you'll probably have much less luck.
Working toward a usable PDA environment in the spirit of Newton OS: Dynapad
Basically, they are working to analyze speech in slices (phonemes) instead of the more computationally intensive task of the whole word. This would lead to a higher success rate and could be easily used across multiple accents of the same language (English, engrish, etc).
I'm excited about what they could accomplish there.
-Cyc
/.'s 10 Millionth
Only recently have PDA's been shipping with anything approaching a good DAC and many PDAs still lack any ADC support. Without a good Analogue to Digital convertor built into the PDA you won't be able to do voice recognition. Remember that your 386 still required a soundcard to work properly. The same is true for PDAs today.
Dictation is fine...as long as the damned thing doesn't start talking back to me.
FoundNews.com - get paid to blog.,
Since the asker wanted to know WHY nobody has done this yet, I'll spell it out:
Basically the major pitfalls to developing this are: :)
1) Crappy algorithms that mangle what you really said into something unrelated
2) Power Consumption
3) Interfacing to the PDA (not hard to do, but non-trivial)
4) Limited PDA capabilities (Remember that Palm's DragonBall is a RISC architecture, and things like speech recognition NEED floating point math which must be emulated)
The solutions:
1) Somebody (not unlike me...) has to code the already existing better algorithms (check the literature - speech recognition is a mature technology, and publications abound) into a usable chunk of code, instead of simply recycling ViaVoice or NaturallySpeaking's libraries.
2) Add more battery storage.
3) Use another processor to do the conversion, then simply write it to the Palm in a serial stream.
I would just wait about a year, then ask that question again to your physician friends, and see what they whip out of their pockets... :)
In the late 90's there were 3 major SpeechWreck vendors: IBM, Lernout & Hauspie and Dragon Systems.
Microsoft poured a bunch of cash into L&H. L&H eliminated some competition by purchasing Dragon.
L&H did some highly irregular accounting tricks, got themselves thrown in jail, and took their comapny down with them.
End result: There is only really one speech recognition vendor at this time, IBM, and they are just useless at marketing consumer products.
Keep an eye on Phillips. They are currently spending big bucks developing their Speech Magic engine.
Your other option is to find a copy of Dragon Mobile. Record an audio file on your mobile, then have it recognized on your PC.
1) Create PDA voice recognition software
.. but on a PDA???? That would be rough!
....
...
2) ????
3) ???? (not profit!!!)
Seriously, TRUE voice recognition is only 99% accutate. It is bad enough trying to make corrections on a regular key board
Why not stick to using your laptop (which has MUCH more processing power) for voice recognition for now? You'll be able to run better software (software that does TRUE voice recognition, not phrase recognition) and have enough memory to run a text editor w/ spell check after you have completed your document.
This might be a great idea, but I think it might be a little ahead of its time
Just my two cents
HallmarkOrnaments.Com
I have been wondering why speech recognition isn't more widely used as well. My conclusion was that there simply isn't enough interest in it. Companies won't make it until consumers are willing to buy it, and the consumers won't buy it until they are convinced it works better (and maybe even then they won't - see M$IE vs. the other browsers).
As an open-source zealot, I have to point out that Free software would be a solution here, as it is less concerned with profits. IBM seems to have open-sourced some code related to speech recognition, and there are a number of other projects out there, but even for open-source, there has to be sufficient interest in a project, and sufficient could mean _a lot_ in this case.
I think speech recognition is great, and I would use it if I used Windows. I just haven't found a good solution for XFree86 yet - not that I've looked very hard.
Please correct me if I got my facts wrong.
Maybe this is a step in the right direction for you: http://www-3.ibm.com/software/speech/handheld/vvms _sr.html
Has everyone missed the key reason here? When we use PDA's, we usually only access them for a few minutes at a time, which is why we're able to get such great battery life. But imagine if the processor was constantly running to do recognition? The battery life would be practically nil...
Palm applications, in particular, are designed around the idea of "forms" -- you put a form up on the screen, and then you sit there waiting for the user to do something. You don't run a constant loop listening to a microphone every minute, because that sucks up the battery like crazy. The Palm programming philosophy says that 99% of the machine's time should be, essentially, idle. Voice recognition, on the other hand, is very processor-intensive -- probably too much so for a pair of AAA's.
Breakfast served all day!
This should work: http://www-3.ibm.com/software/speech/handheld/vvms .html
http://www-3.ibm.com/software/speech/handheld/ipaq _fam.html
My $150 Handspring Visor Platinum has 8 MB RAM, a 33 MHz Dragonball (68000) processor with no cache or FPU. It is claimed to perform at about 5 MIPS, about what a 386/25 could do. It has a microphone, but it is connected to pins for springboard modules only. You have to have a module to use it. The placement of the microphone suggests that it's there so that a cell phone module could be built.
8 MB RAM should allow recording for over 5 minutes, uncompressed, of 22 KHz 8 bit sound. This is pretty good quality sound.
Given that you need a module for this unit anyway, you might add some hardware over just a D/A converter to make speach recognition quicker.
In any case, there's no reason that it can't be done. In fact, there are Palms with cell phones built in that can dial favorites in the address book using voice commands.
-- Stephen.
Lo, many years ago I had a lot of luck with EARS on my 66MHz 486. It's a very simple discrete trainable recogniser; you have to teach it every word before it would recognise it. But it was fast then, it should be really fast now, and was pretty decent for recognising simple commands.
Tiny devices like cell phones and PDAs don't have the CPU power for sexy, high quality voice recognition. They do however have wireless connectivity. So, solve the problem this way...
Install voice recognition servers, network connected boxes with powerful CPUs and the best voice recognition software you can get your hands on. A voice recognition client then just needs to send the voice data up to the server and get the translation back, say 100kbps up and some tiny amount back.
The payback comes because most devices will only use voice recognition for brief periods, so will present a negligible load on the servers. The dictation users will place a higher load on the servers, but even there, I'm guessing there is a lot of pausing involved. I'm also going to guess that some lag is acceptable for dictation. Presumably the person is thinking about what they are saying and proof reading later. This load can be prioritized lower to allow better immediate response for people issuing voice commands on their mobile devices.
Power consumption on the portable device will probably improve. They will have to operate their transmitter (think "talk time" vs. "on time"), but they won't need 5 watts of CPU doing recognition. (Guessing from a mobile G3 PPC, further validated, considering that the CPU spot of my iBook gets far hotter under solid use than a cellphone.)
So, just to pick numbers out of the air, a dual processor, high end commodity hardware voice server might serve 500 pda users giving intermittent commands and 6 simultaneous dictation users.
A company or school could easily justify the hardware cost of this service.
Now, someone go out and build one.
T. Herman Zweibel has returned to us and is posting to Slashdot!
Sir: Last we heard you were rocketing into deep space. What happened? Has your loyal servant Standish discovered the workings of the giant rocket-ship?
We rejoice at having your wisdom returned to us.
Actually if you read the post he doesn't actually say he was happy with it just that the requirements to run it were low. I think he was hinting at the fact that since most times things get smaller and faster that speech recognition software would as well.
The fact is that the speech recognition used to SUCK! It has gotten a lot better since then but only because of the increased complexity of the software.
-Chris
Microsoft Office XP has voice recognition / dictation that ships with the product. You might be able to get a small laptop running Office XP to do some dictation. I don't know how well it works, but if the 1990s application worked for you maybe this one is acceptable.
You don't have to be disabled in some way to think this'd be handy, do you? That's the story for this one person, okay. But if you hadn't heard of a PDA ever before, wouldn't this be one of the most likely functions you'd think of for them? It's a totally natural application for a handheld gadget like that, and one that really would have a natural market among all the middle manager types who made Palms so popular to start with. Right?
(Are there PDAs that can even read text in the other direction, though -- text to speech?)
"Fundamentalism" isn't about divine morality. It's about human authority.
Unfortunately for you, discreet speech is seen as passe by the major players (IBM, L&H, MS). For a long time, continuous speech was seen as the major boundry to widespread acceptance of general purpose dictation software (another boundry was the support of large vocabularies). Eventually, processor power and algorithms evolved to a point that both barriers were overcome and discrete speech (and small vocabs) were left by the wayside.
One byproduct of this was a decrease in voice error correction performance -- Most verbal corrections are single words (e.g., the user selects the misrecognized word, "foo" and repeats the intended word "bar" without any of the coarticulation cues that the continuous recognition engine relies on). The recognition of isolated words by a continuous speech recognizer is inferior to the performance of a discrete system, yet the major software companies removed the discrete recognition engines from their products. (for more on speech errors, see this or this pdf).
Anyway, the use of discrete recognition engines has been essentially abandoned by the major players, and seems to have been relegated to the specialty shops that cater to disabled users. One outcome of this is that there is very little innovation related to discrete speech because it was one of (many) historical barriers to the use of desktop speech reco. I can certainly understand the resistence by the big companies to go back to an "inferior" recognition engine for handheld devices. Most likely, speech reco on the handheld will emerge in a client-server environment with the speech signal (maybe somewhat processed) being sent from the handheld to a server for recognition, and the text being returned to the handheld. We probably won't see a general purpose speech recognition application (as opposed to a limited vocab application) that runs solely on a handheld until continuous processing can be done entirely on the device.
Thanks
Taco
Maybe the way to approach voice recgnition through using air waves is all wrong to start with:
Bowman: "Hello, HAL? Do you read me, HAL?"
HAL: "Affirmative, Dave, I read you."
Bowman: "Open the pod bay doors, HAL."
HAL: "I'm sorry Dave, I'm afraid I can't do that."
Bowman: "What's the problem?"
HAL: "I think you know what the problem is just as well as I do."
Bowman: "What are you talking about, HAL?"
HAL: "This mission is too important for me to allow you to jeopardize it."
Bowman: "I don't know what you're talking about HAL..."
HAL: "I know you and Frank were planning to disconnect me, and I'm afraid that's something I cannot allow to happen."
Bowman: "Where the hell'd you get that idea, HAL?"
HAL: "Dave, although you took thorough precautions in the pod against my hearing you, I could see your lips move."
Why hasn't it occurred yet?
Voice recognition has been "two to five" years away since for the past twenty years. The reason it hasn't occurred because it is too hard. The "two to five" year quote are from overzealous marketing folks.
It won't happen for quite a while because the emphasis has been moved away from wide-scale voice recognition to having specific recognition requirements, such as, recognizing numbers, "yes" or "no," few verbs, or recognizing an individual's voice commands.
You would have to look to academia for answers, because the funds for the research dried up in the comercial market.
Actually, Dragon Naturally Speaking Doctor's Edition comes with a special USB dictaphone that plugs into the computer and translates the voice into text using Dragon's software. I'm not sure if it works with anything but Windows but its certainly cheaper than hiring someone to do it.
You could try running this version of VoiceType within PocketDOS on a Handheld PC 2000 or PocketPC machine... Or, you could find an older PDA that has a 486-class processor. Not sure if PocketDOS can handle sound, but it worked great for running Lotus Agenda on the Jornada 720... Not a DOS shell for WinCE, but a x86 emulator with DOS installed.
Working toward a usable PDA environment in the spirit of Newton OS: Dynapad
The poster's question brings to mind a thought I've had lately, though, on PDAs and smart mobile phones. I've recently 'switched' from a Visor to just using my Sony Ericsson T68 as an organizer. Works great with iSync, etc.
The Palm-with-phone always made more sense to me than the phone-with-organizer. It seemed that the phone part could change shape - I could stick it in my ear in the form of a headset, with a connector to the Palm. A phone I need to hold up to my head. I can't surf with something held against my head that way.
However,
I've realized that I need a phone more, and more importantly, I only enter very small bits of text into the Palm. Furthermore, I spend much more time looking up things than entering things (as I use the Mac do enter data whever possible).
This led me to the conclusion -- the one thing we are missing from the organizer/phone landscape, as the poster asked, is some kind of speech-to-text.
If I could literally hit a button and say "lunch with Dave next Tuesday" and have it enter that as live text... blammo. No more Palm, no more stylus. The phone already listens to voice commands. If it took short notes/appointments, I could literally walk around, call people, make appointments and notes, and not take the thing out of my pocket. Nice dream.
*sigh*
If Jesus wants me it knows where to find me.
ask that question again to your physician friends, and see what they whip out of their pockets
Is that a dictaphone in your packet or are you just happy to see me?
If your bitterest enemies are people who hack the heads off civilians, then I would say you're doing something right.
and it also has 8k of storage! You could store all of "Hel" on that thing
Those were pretty damn old in 1990, when the 486/33 was king. =)
... at least in beta form, from Dragon. Compatible with the Newton 2x00 series, which featured a StrongArm 110 processor @ 162mhz (which is only today being matched by PocketPCs), the big limitation was in the available memory for vocabularies. With 64-128MB of RAM, 128-512MB flash memory in upcoming handhelds, it should be easy to do voice (particularly in an IBM branded Linux PDA? :) recog. Talk about a killer app...
Hey Apple, how about a new PDA with voice recog, inkwell, color, bluetooth + 802.11, compactflash and a small OS X kernel?
See
p aq _fam.html
http://www-3.ibm.com/software/speech/handheld/i
Plantronics makes several headsets with microphone that only require a USB connection, but do not require a sound card. They work quite well, and this should lower the hardware requirements for a small, lower-powered device.
http://www.plantronics.com
and search for their DSP-*00 series. I picked up their DSP-500 (normally $110) for $40 on a deal.
Since when do corporations sell us what we need instead of creating a previously non-existing demand?
zeke
Everyone has gotten so used to the idea that computers will do exaclty what we tell them. SR will never be 100% reliable (or even 99%) because of the noisy communication medium - air. Therefore you will always need some handy error correction protocol (commonly called dialogue). Have you ever wondered about how well people recogize speech. If something is blurted out at random we rarely catch the meaning first time. "What?". If humans have a lot of trouble understanding each other (about 20% error rate) then computers have no chance when it comes to out-of-the-box out-of-the-blue dictation. And computers don't have the benefit of a decade of childhood, not to mention millions of years of evolution. What I'm getting at is that computers need a great deal of context to succeed (to reduce the number of possible interpretations, and therefore the number of ways of getting it wrong). (I'm speech recogition engineer - our company went bust last year - another dot bomb). 1) the algorithms are good (trust me, i've seen them) 2) the training takes bloody ages - it takes weeks (and tera-bytes of data) to get good results across most of the speaking population. 3) dialogue is very hard. 4) actual recognition is fast (we had dozens of simulateous recognitions on 600Mhz machines). The take home message: Train the users. Manage expectations. Say bye bye to HAL.
It is interesting that I JUST did a project on this subject for a Ubiquitous Computing class... My project was called "Distributed Speech Recognition." Here is a link:
Distributed Speech Recognition ProjectI also have heard it through the grapevine that the big voice recognition companies are working on exactly this technology... I wouldn't be surprised if Speech .NET includes support for something like this in the near future. I believe I read on some website that support for Speech API on PocketPC was coming soon...
Everyone has gotten so used to the idea that computers will do exaclty what we tell them. SR will never be 100% reliable (or even 99%) because of the noisy communication medium - air. Therefore you will always need some handy error correction protocol (commonly called dialogue).
Have you ever wondered about how well people recogize speech. If something is blurted out at random we rarely catch the meaning first time. "What?". If humans have a lot of trouble understanding each other (about 20% error rate) then computers have no chance when it comes to out-of-the-box out-of-the-blue dictation. And computers don't have the benefit of a decade of childhood, not to mention millions of years of evolution.
What I'm getting at is that computers need a great deal of context to succeed (to reduce the number of possible interpretations, and therefore the number of ways of getting it wrong).
(I'm speech recogition engineer - our company went bust last year - another dot bomb).
1) the algorithms are good (trust me, i've seen them)
2) the training takes bloody ages - it takes weeks (and tera-bytes of data) to get good results across most of the speaking population.
3) dialogue is very hard.
4) actual recognition is fast (we had dozens of simulateous recognitions on 600Mhz machines).
The take home message: Train the users. Manage expectations. Say bye bye to HAL.
Back in 1990, the requirements for IBM VoiceType were: DOS, 8MB RAM, 10MB of drive space with one of those new-fangled scorching 386-16MHz processors...
Except for web browsing, back in 1990 I'd have to say I was doing everything I'm doing now, with DOS running on a 386. Makes me wonder what real progress we've made. At the time, I ran DesqView, Lotus Magellan, Lotus Agenda. Brief, Word 5.5 for DOS, Borland's Turbo C and Turbo Pascal, TopsSpeed's Modula-2 compiler, the MKS Toolkit (a KSH shell in each DesqView window), and assorted odds and sods. To this day, I've seen nothing on any platform to equal Brief and Magellan, and the rest of the bunch were no slouches either.
Since then, I've spent thousands of dollars on new hardware and software with only a mrginal increase in capability. Yeah, sure, the fonts on my monitor look better, but what price prettiness?
-- Slashdot: When Public Access TV Says "No"
That's the way I read it, yes. Didn't the author only want integrated replayable audio? A little tape recorder functionality in his palm OS device? I didn't see anything in the original article that suggested speech-to-text.
Keep in mind the following: True High Quality Voice Recognition is the next real Operating System Killer "feature". If Linux gets it going reliably before MS, it could wipe out MS, simply because voice commands are so user friendly. If M.S. gets it up and working before Linux does, Linux may end up the next "Apple". That is why MS is interested in it so much, while IBM etc. do not care. True Medium Quality Voice Recognition is the holy grail for PDA type devices. It would allow people to drop the cumbersome stylus / Graffiti / micro keyboard data entry system, freeing up things like the Watch version of the PDA. These things ARE heavily desired and researched, but what you considered to be "acceptable" quality using old hardware never took off because it was not really acceptable - it sucked. The technology - both hardware and software are just not up to most people's needs yet. Try again in 5 years.
excitingthingstodo.blogspot.com
"I'm a writer that is 99% dependent ..."
..."
should be
"I'm a writer who is 99% dependent
speaking of writing.
what?
this guy can't type. sorry it would disturb your sense of aesthetics but he needs vr to DO HIS FUCKING JOB. so i hope it does take off. and when it does, just buy earplugs until you can have some consideration for people who might not be as fortunate as you.
US Citizen living abroad? Register to vote!
If I can find a machine to wash my dishes AND clothing, I'd say that'd be pretty cool!
Dragonball's Motorala's, not Palm's. It is a CISC, not RISC, more specifically a M68K. RISC is usually better than CISC at floating point, but both architectures can go without a floating point unit, and that's what Dragonball does.
Leandro Guimarães Faria Corcete DUTRA
DA, DBA, SysAdmin, Data Modeller
GNU Project, Debian GNU/Lin
It isn't a obsolete term, just an uncommon one. My wife is a doctor and has to dictate patient reports constantly. Guess what they use? Yup, dictaphones. And that is what they call them too. Sure it's nothing more than a voice tape recorder of one type or another but I honestly can't think of a more appropriate term. (more common but not more appropriate)
Some mics do this mechanically also - They have a port on the reverse side of the mic element so it only detects pressure differences between the two sides of the mic, i.e. only nearby sounds coming from one side of the mic (your mouth). Plantronics has plenty of these - Such NC headsets are common thanks to cellular telephone handsfree kits being required by law in some states, and they are quite good. (I love my Plantronics headset.)
retrorocket.o not found, launch anyway?
I used VoiceType for a while, as it came free with OS/2 Warp 4.0. (Anyone remember that?) It was around 1994, and even on an FPUless machine (a NexGen, remember those?), it performed reasonably.
;)), I somehow doubt today's offerings are any better, even if they do take twice the space and CPU time.
A few years later, around 1999, I found myself in college, and a friend of mine had just acquired the latest natural speech product from Philips. Accuracy? Zero, even after we spent hours training it.
Given that hardly anything has advanced since 1999 (except *BSD and Linux
And what is the problems arquitectures RISC have with floating-point math?
I thought this was the place where they shine!
From what I remember, and I may be wrong, but the current series of Ipaq PDA's from Compaq/HP actually ships with IBM ViaVoice on the CD if not on the machine.
q _fam.html
Check out: http://www-3.ibm.com/software/speech/handheld/ipa
Dan
Although on the surface a PDA appears to have the required "horsepower", in reality the handheld hardware is much different than PC.
The biggest factor is that the majority of PDA's have no floating point unit and practically all algorithms for audio applications use floats.
This is the reason there was no mp3 for PDA up until recently, the codecs had to be written with only integer math.
In fact, I was involved in specing a project to port speech recognition to a PDA. The entire project was just about rewriting all the float operations.
Besides that problem, all of the accurate dictation software is not really based on "audio recognition", it's based in contextual lingustic analysis. Raw conversion of speech to text only averages 70% to 90% depending on the clarity of the speaker. All of the accurate systems use context to create high accuracy. For example, the chance that a English sentence starts with "The" is much higher than it starting with "Sea".
For this reason, dictation systems require huge contextual databases and complex analysis subsystems. So the actual reason why there are few "PDA dictators" is probably more due to disk space and access time issues.
'nuff said.
A few interesting things about voice recognition: The approach to date has largely been one of signal processing. Idea being that we have to develop algorightms to map these sound waves to similar speech sound waves. SW like IBM's and Dragon's continually reqires more powerful processors and bigger storage space because they "improve" this software by adding more algorightms and a bigger database of sound waves to refer to. The only real improvements in speech recognition in the past few years have been due to hardware improvements.
The approach is highly flawed because it does very little to recognize that the "signals" are speech, not just random sound waves that need to be matched (somehow) to similar sounds waves. Speech has rules in it's production, it is limited by the articulators (parts of the body making the sound--throat, tounge, etc) and even more ruled by our "innate" rules for speaking. There's this funny little academic field that studies exatly these subjects, called Linguistics.
Linguists know that speech has many levels from which to begin recognizing it, from a high level where we can find Sentences to the lowest level of a morpheme. By processing speech "top down" like this, and chopping it into smaller and smaller more recognizable pieces it is possible to efficiently process speech. (This is a very, very high-level summary of how this could work). Until the APPROACH is made more intelligent, forget about "slim" applications that could run on a PDA, cellphone, or embedded apps like for cars/fighter jets, or for consumer electronics.
This field needs less electrical engineers and more linguists, but all the major players (L&H, IBM, etc) continue on with their brute force signal-recognition approach, relying almost exclusively on more muscular hardware for "improvements".
--Jonathan
The DSP portion of these (Digital Signal Processing) is a large block about 4" x 1.5" x 0.5" in size, and is attached between the USB connector and the headphones. It contains the sound card (or whatever DSP they're using) for the earphones and the boom micrphone. No offloading of stuff to the CPU.
The PDF file with the description of the device mentions Windows and Mac platforms are supported, so it sounds like they haven't written a driver for other operating systems.
The DSP unit is described as a 5-channel, 16-bit, 48kHz data processor from USB, and 24-bit 100dB signal to noise CODEC, with a 32-bit digital audio processing unit.
But don't trust me. Read the brochure yourself on their website.
Everyone would not be using voice for everything...
The keyboard and mouse are much more powerful in their own ways, and I think most programmers might prefer that.
Come to think of it though, imagine a dictation engine tied to your programming language of choice. The number of possible elements is highly reduced, and it might actually be easier to code....
All bow to his Noodliness!! His Noodle Appendage has touched me!
Ack it filtered out my URL.
http://www.dictaphone.com
There are other options. Did you ever see that South Park with the cripple fight? I think if you started a real-life version of that you could make a lot of money. Then if you're rich you can pay someone to take dictation for you, probably a naked girl even.
until recently, the PDA processors were not good enough, but that is changing rapidly (even though there is, in my view, little use for so much power except language technology).
The resulting dictation systems will not replace conventional keyboard input for a while, however, as recognition rates are .97-.98 (accuracy), and that's a wrong word in at least every second sentence. In comparison to low-bandwith input, however, (as in the PDA with the stylus or as in the author's case due to a fine-motor dysfunction), voice recognition is very competitive.
cheers from dublin.
The correspondent said it was working ten years ago, and bunch bozos said it still too hard.
The only reason I can think of is that these small machines aren't as open to general developers as the generic PC, so you dont see as many niche applications.
I didn't mean for him, I just meant I hope it doesn't take off for general business use. I don't wan't people talking like crazy all the time trying to get their computer to understand. I'm glad for anything that helps people with disabilities do their jobs. One of those being my father, who only has one arm. I just don't want to have to listen to everyone speak slowly so their computer will recognize their voice.
"Cellphones are bad enough, imagine if everyone was talking to their computers. The noise would be terrible."
I imagine keyboardless systems that might work by either sign language or whisper systems that translate the positions of the anatomy of your face and voicebox to text.
Of course, it will turn out that whispering is bad for your voice.
Such is the infinite Grace of Popeye.
"speech recognition" "open source"
Even better, the government could just place some microphones around in public/private places and collect much more easily processed. Think "The words bomb and 'bomb', 'martyr' and 'allah' were just heard on floor 2 near room 532."
SRI is trying commercialize its speech recognition system for small devices, called dynaspeak. You can get more information at http://www.dynaspeak.com/. While this isn't off-the-shelf, the version that I've played with is pretty usable.
Due to my lack of NYT registration, I can only point you to this link, which gets you to the NYT article. I assume it will discuss what you are asking. http://nooface.com/articles/01/10/11/1429210.shtml
Good luck in your search.
MP
Made with massively parallel wetware.
Indeed the technology required back then is iin all essence today's PDA's but anything a programmer touches or a marketing peeps see's instantly gets rejigged/revamped X,Y,Z added (sure there is one peep who actualy uses function Z somewhere) and the ballpark moves. You see CPU and technology is like money - the more resources you have the more ways it gets spent. ALso speach recognition back then was just single person with distinct well trained accent/language. Today your'd be hard pushed to get a marketing dept to sell anything that didn;t have flash graphics, Multi user and language capabilities etc etc etc. Yes it could be done and until some software company takes the approch that supermarkets have and does a basic simple range of software then the requirements will keep on mooving on. Best bet IMHO is to use your PDA as a digital recorder and the/A PC to do the backend processing. I mean do you need instant translation - probably not unless it a universal translator and there still aspiring to that nivana.
I think what you are anticipating is the release of consumer oriented NLU software. NLU software does exist for embededded devices as well as for the desktop. In the near future you will see these products marketed.
I have used Sharp Zaurus SL-5500 to capture voice. At low bitrate settings, it creates a small files.
:)
Then you can add in 1 GB Compact Flash cards and have a long conversation recorded
http://www.ajaygautam.com
It looks like Dragon's "modern" products (Naturally Speaking) are still published (& maintained?) by ScanSoft. Some vendors still show the "obsolete" discrete-recognition Dictate available (Dragon Dictate Power Edition 3.0 $189). If you Google for the part number 01-022-24-01 you'll find other vendors.
L&H also took down Kurzweil (the K. that did voice recognition, not the K. music systems co.).
Kurzweil made a discrete recognition system (Voice) that I used for programming for a while when whateverthefuck is wrong with my hands was kicking up.
I ran it on a Pentium 120MHz laptop w/ 1GB hard drive & it worked pretty well.
I still have the CD's, but it'll only run on Win95, not Win98SE.
Discrete is better for programming because continuous relies on the underlying syntax of the natural language (e.g. English) to hint it at reaonable words for ambiguous sounds. In programming, I say things like "left paren eye spacebar equalsign spacebar..."
Dragon's big advantage over Kurzweil was that it could be used completely hands free (including mouse) so they got the disabled market.
The discrete recognizers had to be trained (Voice called it "enrolling") so they'd know how you pronounce the phonemes, but they had huge vocabularies- you didn't have to speak every word, just enough to represent every sound. The version of Voice I had let me add words, so I could add gss_SetPixelMap & other symbols. There was a way to import a whole list of words, so I munged the output of nm & spent a couple of days training it to recognize every function, type, and variable in the PowerTV operating system.
Kurzweil Voice & Dragon Dictate had extensive "correction" features because they made a lot of mistakes. This started as very irritating, but you'd get used to it & you could talk ahead a few words, then correct the 3rd word back, then continue where you left off. When correcting, it would present a list of close-sounding words to pick from or you could spell out the word & add it if it was new.
There was even a "you keep screwing up" helper where you could give it two words that it confused a lot & re-train them.
One problem with speaking discretely (pausing between each word) is that the back of your throat takes more wear & you can start to go hoarse, causing the recognizer to get worse. Yer supposed to avoid carbonated beverages @ lunch.
Instead of running these old apps on a PDA, why not run 'em on a Crusoe subnotebook or something like the OQO?
My buddy in college ran some sort of voice recognition on his 486 (he was handicapped). he had a card in there which he said cost several thousand at the time. this not to say that handheld's today can't do it. but perhaps the cpu power required is at least not THAT trivial
You can do it, just get an OQO!
www.oqo.com!
Perhaps some real world experience is needed in this discussion. About a year ago, an extended career of bad typing habits (probably due to early childhood training on manual typewriters) ended up in a very nasty case of Repetitive Motion Disorder (RSI). Basically the recommendation was to stop typing at all for an extended period of time, followed by extensive retraining. At that time I started working with Dragon NaturallySpeaking.
In my experience, the software does a pretty good job of recognizing dictation. It does a better job if I remember not look at the screen while I am talking, a habit that is very difficult for me. Continuous speech recognition does better if you give it very long phrases as opposed to very short phrases. Yes, the text does require correction, but text requires correction no matter what input method you happen to use. Basically, dictation software means the difference between doing 500 painful words a day, and 2000 easy words a day. I don't need to continuously train the software, only when I come across a new word not in the dictionary. The main problem is that the primary text errors are not spelling typos that are easy to spot, but homonym errors that are more difficult to spot.
The hardest part is that it forces me to change the way that I write. Formerly I was a very "Beethovenian" writer. This term was inspired by the composer's tendency to use literal cut-and-paste to edit his documents pasting on as many as a dozen layers of new manuscript on top of a phrase until it was perfect. When typing, I tend to delete text several times as it is written. Speech recognition works best if you can dictate an entire paragraph and then edit afterwards. In most cases editing is fairly simple because most mistakes come up in the most probable match list. Speech recognition is probably not as good as typing, but for me is certainly better than the alternative of pursuing a career based around "would you like fries with that?" After all, Henry James suffered the same problem later in life and dictated most of his later manuscripts.
My primary irritation is that the speech models work very well for writing expository text, but they don't work very well for writing programming code. It would also be nice if Dragon NaturallySpeaking came with a better text editor, one that can handle multiple files opened at once.
I think the problem with the older speech recognition systems was that they weren't good enough for most people. Also, making them work on low-end processors is a lot of work--it requires a lot of optimization and assembly language programming. The market just isn't enough to make that kind of investment.
"Over the years, my computer use has de-evolved to programming, FTP, email (Mozilla), word processing (OpenOffice) and Ricochet."
I'd say this guy found the magic combination of words to get his article posted on Slashdot. Heh.
"Derp de derp."
Buy a Handera 330... CompactFlash and SD/MMC cards, built in microphone, save directly do them, export in .WAV format to your PC, do what u want with em... one button record, just hold down the record button and it turns on and starts up, no prob, works great. =)
http://www.handera.com/products/330specs.asp
-Don.
Cwm, fjord-bank glyphs vext quiz
So many people make the claim that people doing dictation would be too noisy for an office. Never seen the secretarial pools of the previous generation? Never worked in a call center where EVERYONE is CONSTANTLY talking on the phone? I just don't see why it's so easy to dismiss "dictation" as being impractical. It hasn't been that long since it was THE NORM in offices, I've personally worked in places where the phone thing is standard fare, and I remember my father's office with all the secretaries and their typewriters -- not the nice "quiet" IBM Selectrics, either. Oh yeah, they had ASR-33 teletypes and a couple of IBM printers going all the time, printing orders and invoices. Sure it was a bit noisy at times, but I've seen worse.
-fb Everything not expressly forbidden is now mandatory.
http://www.handspring.com/products/Product.jhtml?i d=240035&cat=170018
If you're doing straight dictation (speaking into a recorder and someone else transcribes it to paper/electronic) this will do ya. 8.5 hours of pure recording enjoyment. It's as portable as you want.
Now if you want to do Speech-to-Text in there to, the ViaVoice/Dragon solutions are more what you're looking for.
Good luck.
-m
http://www.invisik.com
I worked on dictation and dialogue on a PDA prototype at MS several years ago. It was called MiPad and was pretty cool. Well except that it really had to use a wireless network to a computer to get the recognition done.
There are a couple of reasons why this hasn't hit the market yet:
1) the PDAs really are not powerful enough to do decent recognition. Mainly, they don't have good enough audio input systems for reasonable speech quality. Also not enough disk space for dictionary storage. And the cpus are slow and the RAM is too low.
2) at least at MS it is not a top priority to make speech work for disabled users. Outrageous you say? Not so! Turns out when the speech guys approached the accessability guys on the subject, they learned that speech recognition is not workable in most cases where accessability is needed; that is to say, the market for disabled people who cannot use the keyboard but who CAN use speech input is actually quite small. Most people who don't have the motor function to type (or use some sort of keyed input like Stephen Hawking has) dont have the motor function to speak clearly enough for speech recognition to work. Bottom line: other solutions work better.
The user interface and background tasks eat CPU.
There is a symbol set for pronunciation... I don't need the stupid computer to figure out exactly what I'm saying.
If it checked for aspiration, frikatives (don't yet know what this means), poping noises etc, and recorded the sounds and the rate at witch they occured... You might be able to highly highly highly compress spoken language...
to maybe... 100words/min 300 sylables/min 900 phonyms/min 1800 Bytes/minutes The rate you speak would affect the bitrate...
It could be like midi for speaking.
you could record tonal stuff too...
And if storage space is not really much of a problem you could record the sound at a low bitrate, have it along with the sound markup, and compare the two later for extra reliability.
You could then have it process after the speaking is over, do some database searching, and CONTEXT remembering... and NO freaking MUDDLING of curse/taboo words... I'm sure that eats a lot of CPU time...
These stupid programs try to record directly to english... I want to see the phonetics, and manipulate the phonetic database by hand. I don't want to train a stupid program that doesn't let me undo my reading of the wrong line...
The training process could be made so much better by giving the user more control...
We should start an open database of phonetics and meanings... along with context information for use in these...
(It's in my plans)
More ideas: I have a computer program that lets me sing into it, and it tells me what note I'm singing.
Please use [ informative / summarizing ] SUBJECT LINES
Flame me here
Does anyone believe in keeping it simple, anymore?
Most people do, yes, but most companies believe in keeping it profitable. (at least for the few high executives, anyway)
-Adam
I have to ask why you're limiting yourself to PDAs because I'm surprised you haven't gotten a Sony Vaio, or a MicroPC, or one of the numerous HUD/voice combinations that exist. Heck, an iBook is pretty small, too, and you could easily hook up a small video screen to it and keep it in a backpack.
I see that lots of americans can still make jokes about "World Dominstion" or "World Dictation" as in this case. Be happy, don't worry, there is no free lunch.
El Quakero
The new model of the Sharp Zaurus will have a built in microphone and an application where you can dictate notes right into calendar.
Why has IBM not yet taken a keen interest in *BSD?
Karma: Incomprehensible (Mostly affected by posting at +5, reading at -1, and metamoderating everything unfair.)
Sure, a 386 could do vioce recignition, but it required a special card that not only had higher quality sound inputs, but also had some DSPs to do the hard work. When IBM put voice recignition in OS/2 they warned you that a a 486 was not enough. (Several people tried it anyway, and it worked only within narrow limits)
To emulate a DSP required a lot of floating point math. Most PDAs do not have floating point in the CPU because nothing would use it. The few times it is needed emulation is easy enough, just very slow. No problem though because as I said floating point math isn't much used.
Don't forget that PDA cpus are not designed for speed above all else. They are designed for low power, which means they have to compromise something and require extra CPU cycles to get something done.
Finially don't forget power requirements. When doing normal use the CPU is shut down most of the time, and drawing essentially no power. Voice recignition would change that, and your battery life would suffer drasticly.
Maybe the author should check out the Toshiba Libretto or Funjitsu Lifebooks
Just because you have 300 mhz doesn't mean it can do the same as a notebook computer. The CPU on a notebook has additional instructions (floating point arthithmetec), and more importantly it has additional chipset that support the main processor. Most PDA's use Risc processors ie in Palms. The current algrithems use a lot of floating point instuctions, the RISC processors do not have floating point. Most computers have multimeadia chipsets that are in addition to the main processor that most of you are thinking of. You mention only a few companies that have voice reconigtion but there are many more but not on the market now. One of them to watch is Apple it has had voice reconignition but not doing alot of new products with it. Dragon for Newton is the one I still use that takes simple words and does instructions but the Newton is not sold any more. The Newton is I think 100mhz. The Zarus should be able to do it with Linux. I think we will just have to wait. Microsoft will probably not do it because it has not show to be a money maker.
Stephen Hawking doesn't use dictation. He has some kind of finger-controlled input device. His wheelchaircomputer can speak, but that takes practically zero resources - back in the day I could make my Amstrad CPC speak to me - but it doesn't do speech recognition. Totally different thing, and not particularly relevant.
PDAs can use state-of-the-art speech recognition services by using the Distributed Speech Recognition (DSR) schema. All you need is a connection to
a Speech Recognition Service!
Back in 2000 i worked on a special compression schema for DSR purposes. The results were really impressive! : Using only 2kbps data rate you have access to speech recognition from anywhere (PC, pda, smartphone) withought any penalty for speech accuracy!
I am currently making some tests with Zaurus too! (I had stopped working on that for about a year..)
Check : http://www.telecom.tuc.gr/~perak/speech
Dragon's Naturally Speaking was pretty good, VERY good if you really trained it. But not long after it came out, Microsoft announced it would have voice recognition software built into a soon to come version of Windows. And Dragon's stock price dropped like a rock. They were the leaders in voice for years.
Interesting advancements in software dried up with the increased power of Microsoft's monopoly. Don't expect much until their control is ended.
Get a xybernaut or other wearable pc. Expensive, though.
I'd like one of these devices - and I've often wondered if this strategy would be any good:
;)
Instead of doing speech recognition to 'English', recognize speech to a textual representation of the sound (like the international phonetic alphabet - just an example). Transcription errors should be far fewer since you have a smaller set of patterns to recognize. The device should be capable of reading this version of the text back to you.
The memory required to store text is far smaller than that for sound, so I reckon even limited memory devices should be able to handle hours of dictation. When you return to base, a second program on your PC converts the phonetics to words, much like a spelling checker is used to correct transcription errors in OCR.
The philosophy is somewhat similar to that of Graffiti on the Palm - instead of trying to recognize handwriting, they changed the problem to recognizing something similar-but-simpler. I think people would get used to reading notes they've taken as phonetics (as they did with Graffiti), particularly if the PDA was also capable of reading back to remind them.
As for the command mode stuff - I'm in favour of using bushmen clicks for that
-Baz
Here's a bunch of links.
"Linux price to performance ratio: Error: Divide by zero. Continue?(Y/N)"
should be performance to price ratio, unless you mean linux performance=0 so price/performance=n/0.
"The obvious mathematical breakthrough would be development of an easy way to factor large prime numbers." Bill Gates,
If the palm/CE devlopers refuse to make something more than ViaVoice command crap for the palm, why use a palm/ce?
/. about Linux doing Voice recognition. the very nature of linux says that porting it to a handheld should be no chore.
True to life PC's and even linux hand-helds are smaller than ever... These new tablet PC's and a few small XP capable machines are out there.
not sure, but a while back they had an article on
If I'm wrong, let me know.
THE WORLD IS GOING TO END!!!! eventually.
Or my name (Martin) doesn't become "Mardin". There's a glottal stop there, fuckers. It is also not Maaaahahhhhhhhhttiiiiinnnn!
it becomes "Martco".