Why Speech Recognition Is Unpopular With Personal Computer Users
Jan 19, 2010
Why is speech recognition not very popular among personal computer users? Tough question, but here are my guesses.
1) The SR technology is not yet all that good. For decades, we have been promised that SR is "just around the corner", but the reality is that the technology still has serious flaws, as far as easily converting speech to text is concerned.
2) Personal computing, by its nature, is not all that "suitable" for speech recognition use. The major benefits of SR are to that small group of people who need to "report" their actions, such as doctors, lawyers, reporters, detectives, etc........
How fast can a modern speech recognition app' translate speech into text with no mistakes?In my case, 384 wpm, because that is the very fastest that I can speak, and still have another human understand what I am saying. Neither my hardware nor my software limited me, only the rate at which I talked limited me. My computer is a run of the mill model that has a 2.4 GHz Intel core 2 duo CPU. Ram is 4 GB. OS is Vista Ultimate, with all the patches............................
Hopefully this will be a constructive upbeat productive thread, unless the usual trolls pollute this thread.
(SR = "Speech Recognition" to save space)
Just how useful is SR, to Windows users?
That of course depends on the user.
One could say that SR is 100% useless to 99% of the people in this NG, which would be a compelling argument, difficult to dispute.
However we Windows users get SR free, so it would be a shame to waste it, *IF* there is any reason at all for us to use SR.
So, is there a reason?
Yes, a "free form" blog is one reason.
If you have anything at all worth "talking" to another person, then that is a candidate for doing faster and easier with SR.
Of course if you have NOTHING worth talking about...
So it all boils down to _your_ "worth" to other people, as perceived by those people themselves.
To close this post, I have one more thing worth mentioning, namely that our thoughts are fleeting, Great Thoughts often "get lost in the shuffle".
It is only when we commit those thoughts to permanent text that those Great Thoughts can do any good for other people, or even for ourselves.
SR is an excellent way to "capture" your Great Thoughts; I carry around a 3 ounce digital recorder just for this purpose - - - and yes, you have guessed right, my real name is Bill Gates, and I owe my fortune to that tiny digital recorder, which is one important difference between me and you ordinary mortals.
because I CAPTURED my great thoughts, while you let your great thoughts slip through you fingers.
The "Analyze Written Documents" feature of WSR appears to be broken. I try to keep up-to-date on three different SR apps, which is not easy, because of the differences. The three SR apps are:
....using most recent versions of above 3 apps. Without going into the reason _why_ , I would like to be able to speak the following, and have it come out exactly as shown in the two examples below:........
Every time I open an Office application (Word, Excel, etc.) or Outlook, then Speech recognition seems to fire up. When I have my headset plugged in (USB Logitech headset & Microphone) I get a little panel appear which has a microphone icon and it says “Sleeping” or “Try saying “Start Listening””. I have to close this every time. If I unplug my headset & microphone, then on opening the applications I get a pop up message saying “Speech Recognition could not start” with accompanying text of “make sure your audio hardware is working properly and check your audio configuration in the Audio Devices and Sound Themes control panel”.
Every time I open an application it starts, and I don’t find that friendly. Even with the microphone plugged in, and the setting turned to “Off”, it fires up. Just how do I get it to go way for good (and be controlled when I want to use it?) – any ideas? (On Vista Home premium 32 bit SP2)
i was just looking for vista voice recognition and i cant find it anywhere ive check in the vista ease of access and still no luck. is there a website where i can download this from?
Groking speech recognition, there are many subtle ways to fail, as some of you have already found out.
The so-called Help system in WSR is next to useless.
Now that I am well on my way to learning WSR, I can ask my computer the Really Big Questions in life, such as:
1) What is the meaning of life.
2) Who invented toilet paper.
3) If all personal computers disappeared, what real effect would it have on mankind.
4) Is eating beans allowed inside the ISS.
5) Will a USA colony on Mars be democrats or republicans.
6) Now that I can speak directly to my computer by voice, what should I do if my computer suddenly starts talking back to me.
I doubt if WSR has any practical uses for the "average user", but it certainly is fun to play with.
Mark-
-- I was not going to post the following crap, but "andy t" likes it. It gives him purpose in life, to go into one of his long abusive tirades; I can't deprive him of that pleasure.
The following "test" is what I am going to subject WSR to, about a week from now. To pass the test, no more than two mistakes can occur, when I "speak in" this article.
It will take me roughly 3 minutes to speak-in this roughly 200 word medical abstract.
I know, that is a sluggish 67wpm instead of a persons normal 160wpm normal speaking rate, but this slow rate is common for intricate technical dictation.
I copied and pasted this article from its original medical website.
I'm sure most will agree that this is a very stiff "test" for _any_ speech recognition app.
My bet is that WSR will pass this test, but we will see for sure in roughly a week from now.
This week is needed by me to get the rest of my smarts about using WSR.
I know very little about using WSR, as my time has been spent with other speech apps, namely Dragon NaturallySpeaking 10.0 and MacSpeech Dictate 1.5.2
Test abstract begins after line of asterisks
*****************************
Maximizing therapeutic gain with gemcitabine and fractionated radiation.
Mason KA, Milas L, Hunter NR, Elshaikh M, Buchmiller L, Kishi K, Hittelman K, Ang KK.
Department of Experimental Radiation Oncology, The University of Texas M.D. Anderson Cancer Center, Houston, USA.
PURPOSE/OBJECTIVE:
The nucleoside analogue gemcitabine inhibits cellular repair and repopulation, induces apoptosis, causes tumor growth delay, and enhances radiation-induced growth delay. After single doses of drug and radiation, maximum enhancement of tumor response was obtained when gemcitabine preceded radiation by at least 24 h. Conversely, the cellular radioresponse of the normal gastrointestinal epithelium was slightly protected when gemcitabine and radiation were separated by 24 h. This differential response created a time frame within which therapeutic gain could be maximized. In our present investigation, we sought to define the most therapeutically beneficial scheme of gemcitabine administration when combined with fractionated radiotherapy.
All 3 schedules of drug administration produced therapeutic gain; however, when gemcitabine was given more than once in a 5-fraction radiation treatment schedule, normal tissue toxicity increased. The highest therapeutic gain (1.4) was achieved by giving a single dose of gemcitabine (25 mg/kg) 24 h before the start of fractionated radiotherapy.
I have started tinkering with the built in Windows Speech Recognition within my Vista operating system. I find it quite novel that you can talk to the screen and your words come out on it. Granted that I have cheated at times when it goes wrong and I have to type in corrections but I was wondering if there are any experts out there who could tell me how to make this more accurate?
I have also invested in a program called Dragon Naturally Speaking and loaded it onto my machine today. I started tinkering with this but I believe I have to learn completely different commands to that of Windows Speech Recognition.
I see big bucks being spent for speech-to-text uses in business (billions) - but I question if speech recognition has valid use for us "hobby" users. Anyone here use Dragon NaturallySpeaking for trivial uses? If so, what can it do better than simply banging on a keyboard?
To me, it is just an alternative way to create text. Some advantages, some disadvantages over the regular keyboard way of creating text. There are two modern speech app's that Vista users can run on their computers, WSR and DNS. Vista users who happen to use Macs can run three speech app's on their Mac, WSR, DNS, MSD.
WSR = Windows Speech Recognition DNS = Dragon NaturallySpeaking MSD = MacSpeech Dictate
WSR is free, provided you use the built in microphone that comes with your PC. I think a lot of WSR users wind up buying a microphone, which can run the cost up to $50 or $300, depending on the microphone. DNS costs up to $1,600 which does not include all the auxillary hardware and software, which can easily run up the total cost to over $7,000 if you happen to be a doctor. MSD costs $200, microphone included.
Everyone has their own opinion about the value, or lack thereof, of speech recognition app's. Some people speak from experience, others speak from a broad base of ignorance, still others are trying to sell you something, like microphones for example. In my case, I do not really care whether you use WSR, DNS, or MSD - - -my only concern is for the medical community, where I do volunteer work...........
When I'm dictating text to the computer, if I repeat a phrase that I've dictated before (and I often repeat things like book titles), it will stop taking dictation and instead move the cursor to the place where the phrase appears previously in the document. The only way I've figured out to get it "unstuck" and continue taking dictation is to type the repeated phrase myself.
I see that Vista offers Speech Recognition software that allows you to open apps and dictate speech into Word, Wordpad, etc. Does anyone have any idea on how this free Speech Recognition software compares to the Dragon software that I've been seeing advertised on TV commercials?
Does anyone know if you can take a sound file created with a handheld digital recorder and turn it into written text by using the Vista Speech Recognition function?
Pros and cons of using speech recognition (SR) on a "personal" computer in 2009/2010 This might be opening up a can of worms, let's see if I can stick to the subject, without straying off on all the side subjects that might crop up.
1) generally faster than typing 2) frees up hands 3) can be done without immediate access to a computer, i.e. with a tiny digital recorder 4) frees up more of a persons brain, i.e. because speaking is more natural and intuitive than typing 5) can be done while a person is wandering around his house doing chores, i.e. wireless microphones like the Samson Airline 77 have a 300 foot range 6) modern SR apps can be used in very noisy places,such as next to a loud TV, without adversely affecting the text accuracy
I must say I'm very impressed with speech recognition. I'm proud to be one of the stubborn first users to insist to use speech recognition even though I've made my computer use extremely comfortable using either the mouse or the keyboard (hopefully soon I can add or speech recognition).
Am I the only using speech recognition? I'm interested to know if there others using speech recognition, and how they're using it. The entire writing of this post, including opening Firefox, opening my password manager, logging in to and navigating through Vista forums, setting cookie options, editing and posting this thread was done solely using Windows speech recognition without mouse or keyboard (in a record breaking 40 minutes!).
$MS, the same idiots who brought us that turd of an OS called Vista, are doing their usual trick by trying to disguise a bug in Windows Speech Recognition as a "feature". Namely the "New Line" bug, which capitalizes the first word of every new line, whether the WSR user wants it capitalized or not. This forces the user to waste time correcting the capitalization of lines in his text document............
I have used Microsoft Office's built-in speech recognition successfully with Word 2003 on XP. Now I am trying to use Vista's speech recognition with Word 2003.The training program recognizes voice properly, as evidenced by saying a training phrase improperly it won't let you advance to the next screen until you say it properly. So it is hearing and understanding voice.But no words EVER appear in the Word document. Not the wrong words, NO words.When turning on speech recognition with Word open one of two things happen,either:
1. A variety of commands seem to happen sidebars open, dialog boxes pop up, etc.
2. Speech recognition dialog shows "What was that?"
It is clearly hearing and responding. Set mic volume several times, and db meter in speech recognition shows normal response. It's as if it's in what in Office used to be called "command mode" where it only listens for commands, not words.
I mention Office's command mode, but Vista does not seem to have a "command mode," although it is behaving as if everything is either a command or unclear, and never a word. Note that choosing Tools>Speech in Word has no effect. No checkbox appears, clicking the speech option and speaking, then clicking again and speaking, etc. has no effect.
how to run the speech app. (WSR is short for Windows Speech Recognition). I gave up, nothing in the Help section about how to make user-created macros, or user-created commands. Knowing how to do that is absolutely necessary if you desire to get WSR to be even halfways accurate and fast. WSR has absolutely the worse Help section I have seen in ANY speech app. After a lot of searching on the web, using search phrases like: How to Make User-Created Macros. I literally stumbled over this excellent site - After you spend a lot of time and effort creating your own macros and commands, WSR might perform much better, at least I hope so. Let you know for certain in a couple of weeks. It will take me that long to build up a bunch of user-macros and user-commands, guided by that excellent website.
Two of the biggest criticisms of WSR, Windows Speech Recognition built into the Vista and soon to be released Windows 7 operating system were:
1. No easy method to transfer, backup and restore one's user training profile.
2. No way to keyboard corrections into the Alternates Panel, the corrections box of alternate choices for words that were misrecognized.
We're now pleased to announce the WSR team at Microsoft has released an easy to use transfer, backup and restore tool. Rob Chambers of Microsoft's Speech team suggests: "Be sure to download the release notes as they contain useful information as well as user instructions. Please note that this is a "technical preview" version and as such there are a few known issues with the tool."
I don't own a Mac but I bought a Vista machine from Dell. I asked to return it because it ran so slow. They offered to install XP as it was the only way to make it run at a decent speed. Here are the facts,
1. XP is still going strong because computer manufactures don't want to sell slow machines.
2. Microsoft it self is so mortified by the slow performance of Vista that they are talking about introducing a new OS next year.
3. It is physically impossible for Vista to run as fast as Mac because they use the same chips and Vista devotes most of its memory watching the computer user......
The computer is less than 2 months old. We have four Users accounts set up on the computer and they are all setup as Administrators. When we switch between users the computer freezes up. The computer screen goes blank and a "NO SIGNAL" comes on the screen. I have to press the power button and the computer shuts down and then I can restart it. It happens every time. If I select the Start button then "Switch Users" it will go to the user I select but when I try to switch back the computers freezes, no mouse, no cursor, no key board, it flashes No Signal and then just a blank screen.
I have restored windows to earlier configurations, I have researched the problem on the internet through Google, I have gone to Microsoft's web site and searched for the answer and I have contacted Gateway and they had no idea. I created a Recovery Disk, backup all my settings and files, installed the recovery Disk and restored all the backup files, reinstalled all the programs and I still have the same problem.
I would like to set up a single set of Windows Contacts which can be used by the two users on my machine, such that any changes made by one of them is visible to both. I have tried creating a shared contacts folder but Windows Mail will not then treat this as the Windows Contacts folder for email purposes. Does anyone know of any obvious solutions I am missing?
I calculated that to migrate to Vista or Windows 7 will cost close to =A32000. not including my time - It will take around 100 hours. This is because many of my existing software / tools / utilities does not work on Vista and the vendors expect me to buy a new license because it is a "new product" even though it does exactly what it did before - just on a different OS. Even the products that do work have problems and glitches that have to be worked around. All this takes time MY VALUABLE time. In other words I am suffering because Microsoft want money. In the past some versions of windows were worth migrating to Windows 2000 and Windows XP were great
But most of the improvements to Vista / Windows 7 are mostly transparent to normal users - even monster power users like me. I believe Microsoft have a serious attitude problem. just wait until they take full advantage of TPM to screw even more money out of us. If I am wrong please point out a real tangible benefit that Vista or Windows 7 brings to a large percentage of users or to me. I also I can no longer buy a laptop because they only come with Vista GPU drivers (some come with buggy unsupported XP GPU drivers - great)
I am trying to transcribe an interview and tried a program called "wave to text" but when downloaded it seemed to have a virus with it and, even worse, would not work. Can vista take an audio file and transcibe it?
I accidentally deleted couple folders in my "personal folder"... can't find them in Recycle Bin... so how do i get those special folders under Personal Folder back?!
Don't recall doing anything unique. Exited Windows Mail normally. Next time i accessed my personal folders, excepting one, were gone. Is there anyway to recover?
When ever i try to open my personal file (the one that contains my pictures and Videos and stuff) it crashes restarts and i get this:
Quote: Troubleshoot a problem with CyberLink Demultiplexer CyberLink Demultiplexer has stopped working properly. CyberLink Demultiplexer is a codec. The file name of this codec is CLDemuxer.ax........
My question is how come when a hard drive (Maxline III Model: 7V250F0 SATA) is initialized within windows XPPro and partitioned/ formatted and can be used in XPPro, when WindowsVista Home Basic on the same machine does not recognized the drive except in disk manager it shows the drive without drive letters? I have XPPRO installed on drive 0 and Vista Home Basic on drive 3 in a dual boot with vista boot pro. Noticed the bios has it as a master drive along with another drive on an IDE which is a master too? I tried initializing in vista without any luck? So I tried using after initializing with XPPro and Vista Home Basic wants to load drivers for hardware but can't find any? I am confused! Anyway the drive was out of a Dell computer originally (possibly an OEM drive?) and I used a utility from their web sight to erase the drive. Then I did as mentioned above............
When go into security center on Vista, it says I have 2 firewalls enabled. Windows Firewall and McAfee Personal Firewall. I cannot find MPF anywhere! I want to delete/disable it. Anyone got any ideas on how to?
Note: I'm not using McAfee. It came with my computer and I stopped using it after the 30-day trial.
