Good Cross-Platform Speech-Recognition Programs? 175
CryoStasis writes "I am a graduate student getting my degree in biomedical sciences. Because my work often requires me to maintain a local sterile environment (under a biological hood) I find that I am unable to physically touch my computer, which sits beside me, in order to open my notes, protocols, etc. while I'm working. As a result, I have begun to search for a voice-recognition program that will allow me to tell the computer what files/programs to launch. I know that the general field of voice recognition has come a long way, but I find that the built-in speech recognition systems in both OS X and Vista are clunky and difficult to use. Are there any good, cross-platform speech-recognition programs available that might fit the bill?"
Use PocketSphinx (Score:5, Interesting)
Re:Use PocketSphinx (Score:4, Informative)
I used Sphinx4 in my final year project at uni. It's free and Java based, with open source code so is fully customisable to those who want to spend a little effort doing so. As it is written in Java, it works on any operating system with a Java Runtime Environment.
In the process of finding Sphinx4 I spent a lot of time trying other multi-platform software, but due to its open source nature found this to be the best (that actually worked).
Re: (Score:2)
Re: (Score:3, Insightful)
Uh, isn't that VOIP software? Maybe you could spend at least, say, 4-5 milliseconds explaining exactly how VOIP software is supposed to solve the problem?
Re: (Score:2)
Re:Use PocketSphinx (Score:4, Interesting)
Nope, there isn't. (Score:5, Informative)
Dragon Naturally Speaking is as close as it gets. And it's only really good for basically writing down your voice, it's not really that good for controlling your computer. I believe it works in both Vista and OS X.
There used to be ViaVoice that also worked in Linux IIRC - but it basically stopped working on it circa 2001/2002.
Perhaps another input device is called for, because voice recognition right now will only frustrate you more than anything for what you want to use it for.
BTW, I believe OS X has voice recognition built in you may want to check out for controlling your computer - but it's been ages since I used it. It's actually geared toward controlling your computer, and not to replace typing.
Re:Nope, there isn't. (Score:4, Insightful)
BTW, I believe OS X has voice recognition built in you may want to check out for controlling your computer
I know reading articles is verbotten for slashdotters but the summary???
I find that the build in speech recognition systems in both OS X and Vista, clunky and difficult to use
Re:Nope, there isn't. (Score:5, Interesting)
I, for one, read the summary, but would like to contradict it.
I got RSI and finished a 100-page document using Vista voice recognition only. Just train it properly with a good mike and it's perfectly ok. Apart from dictation, you can say a word in any link or button in properly coded apps, and spell stuff out using the radio alphabet. Alternatively, you can use the commands "mousegrid" and "show numbers" to move the mouse directly or label every control with numbers, respectively.
Oh, and if you get RSI, don't even think about trying to configure anything in Linux until you recover. Ditch it for Vista on day 1. Your hands and sanity will thank you.
Linux users don't get RSI (Score:2)
They learn to script instead.
Re: (Score:2)
Same here. The mouse is a killer with RSI after a while, but the keyboard only bugs me if I'm typing for a couple solid hours. Linux helps a lot, letting me configure things so when it does start to become a problem, I'm not totally knocked out, or forced to suffer to finish a project. Of course, micro-softheads can't admit that their billion dollar company is getting it's tail kicked by free software, so they have to spam IT sites with comments that don't even address the question.
Speaking of the questi
Re: (Score:1)
I wanted to start a project (here is the idea [sourceforge.net]) that would give you a speech interface to a limited, user-defined set of commands. The user should be able to train the program and add new functions/commands.
Advantages: No huge/near-complete databases required, language independent, gets better the more it is used.
However I'm not that familiar with Speech Recognition limitations, and no one has explained me yet, why such a project hasn't been started yet.
Maybe it's just stupid and naive.
Re: (Score:2)
The OS X stuff is fun, but you can't tell it to do enough yet to make it useful. For example, "Look up Bobcats on Wikipedia" is not a possible command unless you explicitly code in Bobcats... Which ruins the point.
Re: (Score:3, Funny)
Wouldn't it be something like "Browser, Address, Spell, w, space, b, o, b, c, a, t, s, Enter". I wouldn't expect completely natural language parsing for quite a few years yet.
Incidentally. I tried the Vista speech recognition (got a computer in Jan 08 with it preinstalled) by running the tutorial. I was amazed, it was awesome, recognised every word I said. Then I said the wrong word ... and it typed the right one. Hmmm. It was actually just detecting a sound and printing the expected word - fooled me for qu
Re:Nope, there isn't. (Score:4, Interesting)
That sounds more like training than a tutorial. If it was training on your voice and you said the wrong words I'm not surprised it got confused and produced gobbledegook.
Re: (Score:2)
Could it spell gobbledegook?
Re: (Score:2)
whatever.
Dragon Speak (Score:2, Interesting)
He has a laptop, and needs someone to turn his computer off and on. But, seems to do pretty well from there, at least for searching the internet. He also buys and trades stocks with it
He had to hire an expert to customize his laptop. So, while it's currently possible to do, it's probably not something that you can do easily.
Is it cross platform? Know idea. He uses windows xp.
Re: (Score:3, Interesting)
Re: (Score:2)
Paper (Score:5, Insightful)
Re:Paper (Score:5, Funny)
I can't say I've ever been in a biolab, but the idea of someone working in one, with their hands in a sealed box manipulating god-only-knows-what... and then trying to talk/use a computer at the same time give me the hebejebees. I can think of at least four hollywood horror movies that started with similar premises. Sometimes a simple low-tech solution really is the best... and it saves on zombie attacks.
Re: (Score:1)
If you are going to mediate reality through Hollywood, you might as well count on Will Smith to save you in the end.
Re: (Score:2)
Wait, Will Smith isn't real?!!
Re:Paper (Score:4, Insightful)
The tags on the summary say it best 'useanundergrad'
There are somethings that really just work best when you have an assistant or partner working with you. It's like sports, well most of them, you need a team to get the job done right.
Re:Paper (Score:4, Funny)
Yes, but like most geeks... he wants to do everything himself. God forbid a man ask for help...
Re: (Score:2)
Re: (Score:2)
Because, as Encyclopedia Dramatica clealy states, "There are no girls on the internet". So it's insightful, because someone's 'nerd rush' has allowed them insight into their feminine side.
Re: (Score:2)
I really, really hope that you were being sarcastic ...
Re: (Score:2)
Only four? I think that describes every horror movie that doesn't feature a faceless psycho, a supernatural monster, or a giant ape. Bear in mind that such movies always feature the improbable. This is by design, because they wouldn't be so comforting otherwise.
Re: Zombies (Score:4, Funny)
You: "Wow. This virus interferes with T-Cells, even reanimating dead tissue. That's really wild!"
Computer: "Command accepted. Releasing virus into the wild."
Re: (Score:3, Interesting)
With e-Ink readers like the DR1000S (and the DR1000SW coming soon and Plastic Logics coming next year) - this may be the way to go without having dozens of printouts. Iliads products has a wacom screen you can write and annotate upon, which makes it almost as good as paper.
Personally, I will wait a few iterations until they perfect these products, but not carrying a bundle of papers and just pressing a button to get to the next page is precisely the advantage, amongs others (like search).
Re: (Score:2)
Yes, seriously, do what the rest of us do when we need to do tissue culture - use a lab book, and prepare your experimental plan carefully ahead of time. Write out the quantities of stuff you need (remembering this was always hardest for me). Unless it's something like splitting cells you should be writing the experiment down for legal reasons anyway.
You'll probably need to bring things in/out of the hood occasionally in almost any experiment, so just make use of that opportunity to look over your notes aga
Re: (Score:2)
Re: (Score:2)
MRI chambers due to the poor interactions if high magnetic fields and a lot of computer equipment comes to mind. Other radiological work has similar issues: biological work where it's easier to destroy paper than to sterilize computer also comes to mind.
Re: (Score:2)
Re: (Score:3, Informative)
Re: (Score:2)
Re: (Score:2)
I don't see why it's impossible to make an autoclave-compatible non-magnetic-sensitive membrane keyboard.
Re: (Score:2)
Paper isn't exactly ideal for keeping things sterile. Are you typing in your handwritten notes later? Are you replacing the printouts regularly?
Why not just use ceran wrap on the keyboard (change frequently)?
Re: (Score:2)
An easy to clean board and disposable wax pencil work pretty good. Depending on your lab, a hanger for the board on the lab window will help keep contaminates in/out of the lab, while allowing you to check your notes as needed. Paper and lab books run the risk of bringing things in/out of the lab, and constantly sterilizing items has it's own problems.
The best solution, of course, is to use a provided, sealed system, linked to your own system outside the lab area. Upload your info (matlab formulas, previ
Vista (Score:2, Funny)
Here's a Video [youtube.com].
Re: (Score:2)
Fail recovery FAIL.
Fail recovery WIN [youtube.com].
depends... (Score:4, Insightful)
Yes, software exists. But most likely unless the program only performs simple operations with dialog boxes and can function with only limited keyboard input, you will probably find it inadequate or klunky, even if the speech recognition is perfect (it never is). Instead of asking whether speech synthesis software is right for you, the better question would be is your software a good fit for speech synthesis?
Kaiser Uses Dragon (Score:2, Informative)
Kaiser MDs use Dragon.
Why must it be cross platform? (Score:2, Interesting)
I'm thinking you're only using one computer for most of your work anyway.
How important is cross platform - or is that just what the cool kids say these days?
Re: (Score:2, Informative)
We use mainly OSX macs in the lab, but if possible I would also like to install the program on some of our other Vista machines for hands free use.
Re: (Score:3, Funny)
Alternatives (Score:5, Insightful)
Re: (Score:3, Interesting)
Re: (Score:2)
Why not sterilize the keyboard? (Score:2)
This isn't directly an answer to your question, but why not put a keyboard/mouse in the hood and use that? A wireless keyboard, perhaps, or it shouldn't be too difficult to put an interface through one of the existing ports. They even make some smaller keyboards that take up less space.
Re: (Score:1)
The main machine in particular is an OSX laptop. Can't really sterilize it without... issues...
Re: (Score:1, Insightful)
You are constraining yourself into bad solutions to your problem.
You have a bad process, and are trying to find band aids for it. The correct thing to do would be to fix your process so that you don't have this problem.
As someone else pointed out. Get a wireless keyboard. Sterilize it.
Re: (Score:2)
So add a USB keyboard on; sterilize that. I'm sure someone has sterilized a keyboard before; even if it's as simple as putting it in a sterililizable bag or something.
Three words (Score:5, Funny)
Cute summer student.
Re: (Score:1)
I'll have to keep that in mind.... LOL
Re: (Score:2)
Cute summer student.
Alterior motives and humour aside, a human assistant is actually a very good idea.
Re: (Score:2)
And flipping pages is one of the things that undergrads actually do quite well, even without lots of training.
I do love the "insightful" mod though.
Re: (Score:2)
Plus, if said student's annoyed with your harassing behavior, they're far more willing and able to jab that atropine needle into your heart.
Of course, they might "accidentally" wiggle it about a bit, too...
Re: (Score:2)
My PhD supervisor has said that his ideal lab would be all guys... or all girls, he really doesn't care which, so long as there isn't a mixture.
Naturally he's never even come close to that ideal.
Lets Recognize Speech (Score:2)
or..
Let's Wreck a Nice Beach.
Yeah, there's no such thing as "good" speech recognition yet.
Re: (Score:2)
I thought the quote was:
"It's hard to wreck a nice beach."
- unknown speech recognition software
Put a keyboard in the box? (Score:1)
Can you do somet
You might want to consider alternate peripherals.. (Score:3, Insightful)
For some years now, there have been pointing devices for the disabled that essentially involve an IR webcam and a reflector or LED stuck to whatever part of the body the user can still move. http://www.naturalpoint.com/ [naturalpoint.com] make some such, I suspect that they also have competitors. On the cheap side, there has been a fair bit of buzz lately about using video processing software with ordinary webcams. A bit of googleing should turn up stuff for Win, Mac, and Linux.
On the keyboard side, silicone rubber flexible keyboards have proliferated alarmingly of late. The keyfeel is bloody awful; but they are cheap, fully sealed against moisture, and can survive cleaning with various moderately horrible solvents.
With a simple USB hub, you should be able to leave the keyboard and webcam in the hood, never having to touch the webcam, and dousing the keyboard in whatever horrible substances are necessary to keep it sterile, and just plug in the one USB cable to your laptop before you begin work. Not wildly elegant; but it should provide you with a standard keyboard and pointing device that fulfill your requirements.
Wii hack it (Score:2)
For some years now, there have been pointing devices for the disabled that essentially involve an IR webcam and a reflector or LED stuck to whatever part of the body the user can still move.
Sounds like one of Johnny Lee's projects [youtube.com], you could probably accomplish this with a Wii-remote and his free software. [cmu.edu]
teamwork (Score:4, Insightful)
There is no substitute for teamwork. I don't work in a biologically clean environment, but I do sometimes work in a vacuum clean environment which requires that I avoid touching anything that isn't cleaned to go into a UHV chamber. Having a teammate to work in the "dirty" environment in the rest of the lab makes things much, much easier.
The progress of research is never perfectly predicable, and you're always going to find some surprise which needs immediate attention. Having another person there means you don't have to prepare in advance every possible command you may need a computer to run, plus a person can do things like answer the phone and sign for deliveries. It's also good practice for later in your scientific career when you'll have to train and trust your own students/interns/employees.
Keypad + Nose (Score:3, Interesting)
Get a numeric keypad, and pop off every other button cap. Map the remaining keys to whatever actions you want to control on the computer. Tape the keypad to the window on your hood, perhaps with blue masking tape (removes cleanly). Hit the buttons with your nose.
On Windows, I would get all the files opened, and have a key for Alt-Tab, and then keys for left, right, up and down.
Good Luck!
Undergrads (Score:1, Funny)
The best (and cheapest) speech recognition program is "undergrad". It will open anything you want on your computer, and even read it back to you. Sometimes it just stops working, though, so you might have to keep getting newer versions as they become available.
foot mouse (Score:2, Interesting)
You can get a mouse that you can operate with your feet. Would that work?
footsie mouse (Score:3, Interesting)
Shame you're sitting unseen. There are foot controls for the simple stuff he's asking for. Now if he wants to do something more complex then the voice option is the viable one.
Try a Laser Keyboard (Score:5, Interesting)
they are awkward but pretty cool. It's a virtual keyboard projected onto a flat surface which could be sterile. There's zero tactile feedback but you can use it for simple stuff.
Example
http://www.virtual-laser-keyboard.com/ [virtual-la...yboard.com]
Re: (Score:2)
That looks like a pretty cool toy - too bad there are no linux drivers yet. On the other hand, there are a lot of drivers for commonly-used devices. I wonder how much these would quiet down an office full of cubes with people pounding on noisy keyboards.
Re: (Score:2)
It claims to be a standard HID Bluetooth keyboard, so it shouldn't need special drivers for linux - the included ones will work fine. Note that the drivers for windows (post 9x) are also optional, as they support bluetooth out of the box, and OS X also works fine out of the box.
One day there will be (Score:1, Interesting)
http://voxforge.org/ [voxforge.org]
Re: (Score:2)
More on Dragon Systems (Score:5, Insightful)
Dragon Systems is by far the best speech to text resource. I use 9.0, but 10.0 is out. And by all accounts it is better. Like all good tools that have power and flexibility Dragon takes some time to master. But it is intelligent and repays hard work by improving. Suggest you get Dragon Preferred or, at a minimum, Pro. With these you can also make audio notes on a stand-alone recorder which may be fed in to the program later for transcription. If the audio is good (use a headset) the results are very good. Of course it needs an editing treatment, but what draft does not? So, you could make notes in addition to controlling the computer.
I suggest you practice at some time when your hands are not busy playing with the Andromeda Strain. And if you get skilled with Dragon you can swap modes; that is, speech to text or control mode.
The hard truth is this: Speech to text is something you have to learn how to do. Even if the program is perfect there is a learning curve for verbally inserting punctuation. And for writing with your voice. Nine has a feature to do punctuation automatically, but it works as poorly as most stenographers. In another life I used to dictate to a secretary who took shorthand. Even with her I interposed punctuation. And I can tell you...It really took me some time to learn her curves. Drum Roll Please
Extra keyboard and mouse? (Score:2)
Re: (Score:2)
There are some vandalism-proof keyboards with stainless steel surfaces, which should survive a lot of "soft" sterilization methods like surface disinfectants, highly UV resistant, basically anything less demanding than an autoclave. An example can be found here: http://www.industrialkeyboard.com/html/vandalism-proof_stainless_stee.html [industrialkeyboard.com] (even comes with an integrated trackball).
Build a terminal (Score:2)
Try thinking in terms of a voice activated keyboard instead of a voice activated computer without a keyboard.
What is the real problem? (Score:2)
What is the real problem you are trying to solve?
Why is it you think you need access to your computer? Surely there are ways to record your results without recourse to a computer in a sterile environment. I mean seriously what is wrong with a notepad and a pencil? In the days of Newton, Galileo, Einstein, Lavoisier, Lord Kelvin, Darwin, Planck, Curie etc that was the best technology available and yet, amazingly, they were still capable of good science
Re: (Score:2)
Yeah why do they need that particle accelerator, people have managed with cloud chambers for decades ....
I agree, he should state the exact problem rather than assuming he knows the solution but can't implement it. But your argument is spurious. Perhaps he needs real-time graphing from sensors or some such?
My vote is for the "wiimote whiteboard" projected onto the work bench (with an onscreen keyboard) or simply a projection keyboard.
Dragon, vmware and a named fifo? (Score:2)
How about some sort of vmware (or kqemu etc) hack using dragon, then either write to a named pipe (if that's possible), or
make the file network mounted, and auto-save every 10 seconds? Actually, you could set Dragon up to input into a browser text-box, and do some AJAXy stuff to capture stdout....
Re: (Score:2)
Re: (Score:2)
Thank you - that looks really useful. I'll give it a go...
Gestures via webcam (Score:2)
Software such as web browsers can perform actions via mouse gestures. But what if you don't have a mouse? Use a webcam!
Google "gesture webcam" and you'll get links to demos on youtube and software. I'm not sure how mature this idea is but it sounds cool!
Have no keyboard? learn sign-language! :) For deaf people that can sign faster than they can type researchers are developing webcam recognition [tjhsst.edu].
Those that don't grok sign-language could potentially use character-based gesture input modeled on Palm's G
Wrong question (Score:5, Insightful)
You don't want voice recognition. You want basic planning and lab book management skills.
You should be asking "Why didn't I get all of my protocols, reagents, samples, and equipment set up before I started my experiments for the day?"
I did quite a bit of biochemical benchwork to get my PhD, involving flu. Touching almost anything was either a bad idea for your health, or a worse idea for your experiment.
Instead, you laid out a plan for what experiments you were going to do for the day. You wrote it up in your notebook before you started. If you were doing a standard experiment, you probably had an easy excel template where you typed in the number of replicate experiments you wanted to run, and it did all of your calculations for you. Print it out, tape it in your notebook, grab all your samples and reagents from the freezer, and then (and *only* then) did you put on your gloves and go into the sterile hood.
My old lab book is *full* of these little protocols, usually with a typed note at the bottom about which samples I wanted to run, and a few hand written notes from after I took my gloves off.
For long, complex protocols, lay out a protocol book with step by step instructions. For really sensitive experiments, don't be afraid to change gloves after you flip the page. Gloves are cheap, compared to the reagents needed to run even a single PCR reaction.
A good craftsman has laid out all of his tools, plans and materials before he starts work. Good chefs have all their ingredients measured and utensils easily accessible before they start cooking. Either one *could* use a computer to track their project. But they don't, because it just makes everything more complicated.
Use a computer for planning, data storage, analysis, etc. Once you put the gloves on, good notebook skills put the computer to shame every time.
Re: (Score:2)
Why didn't you just turn pages with a forceps?
Re: (Score:2)
"You don't want voice recognition...."
Just use what everybody else does. Dictate everything into a dictation device,mp3 player, smartphone and type it (or let it type) afterwards.
Much, much faster really.
Touchscreen (Score:2)
Why not simply purchase a touch-screen panel, and bring that into the hood with you? If you get a resistive-touch version, any object can be used -- including your sterilized aluminum stylist -- or a chop-stick. And because it's resistive, you could even use it through another substance, even through your hood itself. It's a simple USB cable to the computer, so you could keep it far away from the computer, and use it as you would a tablet.
Good speech recognition doesn't exist anywhere (Score:5, Interesting)
I'm a grad student in computer science, specializing in AI. Although it is not my forte, I have studied speech recognition a fair amount, and I am friends with professors and grad students who are on the cutting edge of ASR.
Unfortunately, the real answer is that, at least by my standards, there is no good speech recognition anywhere.
One of the most challenging things about human speech is what we call "lack of invariance". The same word can be said by the same person two times in a row, within exactly the same context, and the signals will differ to an amazing degree.
At this point, if you have a hand-segmented accoustic signal, where the phone boundaries (such that there are any) are already marked, we have recognition rates exceeding 90%. But if the signal is not already marked, where the ASR machine has to segment automatically, the rate goes down dramatically. Then you have to recognize words, where the realization of any given word in any give context is not necessarily consistent with how you would typically describe the word phonemically. We see it all the time where what's in the accoustic signal is actually quite different from what the listener hears. It's really quite frustrating.
In my opinion, the accuracy of even cutting edge speech recognition software is pretty miserable.
Re: (Score:2)
Re: (Score:2)
Well, I sound like I'm from Ohio (because I grew up in Tampa, FL), so I don't have that problem either. And to tell you the truth, ASR systems perform almost acceptably with my speech, either my native "neutral" US accent or my fairly decent imitation of UK Received Pronunciation. However, my classmates from India and China have no hope.
Simpler method... (Score:2)
Sterilise a keyboard, perhaps with one of the silicone covers that you get for using computer keyboards in sterile environments. Seal it into your sterile box. If you're really fussy, use a wireless keyboard so you don't even need a gland to take the cable through.
Dragon Naturally Speaking is it... (Score:3, Informative)
Period, end of report. In the PC world there essentially is no other general purpose voice interface tech that is even worth bothering with.
That being said, there are much better ones for very specific vertical markets, but not for general use.
Note that this means you ARE restricted to Windows. The stuff built into OSX and Vista are not even worth messing around with. They might in theory meet some very casual or narrow specific need of particular users but they are literally an order of magnitude slower and less reliable than Naturally Speaking.
If you MUST use a Mac or Linux etc then basically the answer is, you're SOL, there's nothing. Yeah, there are a few OSS bits out there, but frankly they aren't even at the level of being really functional software, let alone meeting speed or accuracy required from this type of software. It would be AWESOME if there was something open, but the fact is this area is just so technically demanding it appears to be beyond the reach of non-commercial effort.
command control vs. dictation (Score:2)
Re: (Score:3, Interesting)
Autoclave - will leave just a pile of melted plastic in place of kb+mouse.
Gamma rays - not sure of dose, but may play havoc with the electronics inside.
Ethylene oxide - yes, but how common is that? I used to work in a lab in a big university/major city and we didn't have ethylene oxide facilities. Only autoclaves.
I would suggest: seal kb and/or mouse in a plastic pouch, and use a chemical method to sterilize the outside of the pouch (bleach, etc). To change batteries, cut pouch open, put new batteries in, p
Re: (Score:2)
I would suggest: seal kb and/or mouse in a plastic pouch, and use a chemical method to sterilize the outside of the pouch (bleach, etc). To change batteries, cut pouch open, put new batteries in, place in new pouch and repeat.
The flaw in your plan with sealing a computer in plastic is the fact that it relies on a fan to cool itself. Cut off the air, and it burns.
Re: (Score:2)
Please read carefully. I suggested sealing the keyboard and mouse, not the whole computer.
Re: (Score:3, Funny)
So you're a grad student in the sciences and write "build in" instead of "built-in".
Don't rag on him, it was his software. He originally said "included."