Speech Recognition 2002:
Real Uses in Real Life
Note: This online version has been updated with added material on How to Succeed with Speech Recognition and on backing up NaturallySpeaking speech files.
Wells H. Anderson
President, Active Practice LLC
800.575.0007
Helping lawyers leverage technology
ABA TECHSHOW 2002
March 14, 2002 – 9:00 am
Special Features of Dragon NaturallySpeaking
Speech Recognition Stumbling Blocks
Compatibility with Specialized Programs
How to Succeed with Speech Recognition
Summary
Computers that act on verbal commands and take dictation are no longer just the stuff of science fiction. But you can't just buy a microphone, plug it in and expect results. This program goes past mere dictation into designing verbal macros and other command-based tools. Our panelists will cover the available speech recognition products and give their best forecast of this emerging technology.
In addition to covering requirements for speech recognition and the tools included in the software, the session and these materials address the following question:
What problems cause speech recognition projects to fail?
Does It Work?
Most people interested in speech recognition, also referred to as voice recognition, have one burning question: "Does it really work?" Many of us are skeptical, figuring, sure, it works for experts and for carefully trained company representatives, but what about for regular people? Won't it be more trouble than it is worth?
My response sounds all too familiar: It depends. The good news is that it depends on a lot less than it used to. The bad news is that it still takes a significant investment of time and money. Those who follow good advice and invest their time wisely will find their investments returned handsomely.
Speech recognition technology seems deceptively simple: You talk; it types. What that simple view omits are the many differences between the creation of oral and written communications. In order for you to determine whether speech recognition may work for you or for your staff, you need to know more about the nuts and bolts of writing with a microphone, software and a computer.
Here we consider the use of speech recognition from a number of different perspectives. How do the competing products differ? What hardware do you need? What are the different skills you need to have or learn? What features of the speech recognition software will you need to use? What factors affect how efficient you can become?
Summary of Competing Products
Dragon NaturallySpeaking
Dragon NaturallySpeaking pioneered affordable continuous speech recognition. http://www.lhsl.com/naturallyspeaking It has been acquired by ScanSoft from bankrupt Lernout & Hauspie.
While some past reviews of speech recognition accuracy have given the edge to IBM ViaVoice, Dragon NaturallySpeaking has won most of the accuracy competitions. Reviewers clearly place Dragon NaturallySpeaking in the lead in the areas of usability and features.
The verdict is not yet in on the latest version of Dragon NaturallySpeaking, Version 6. Some have reported stability problems. It needs significantly more horsepower than Version 5. We recommend a Pentium 4 or advanced Athlon chip and 512 MB of RAM. Prices have dropped more sharply over the last year than in previous years, so stiffer hardware requirements are not so large an obstacle.
Dragon NaturallySpeaking shines in the areas of usability, accuracy and documentation. But many people who try it fail through no fault of Dragon NaturallySpeaking.
IBM ViaVoice
IBM ViaVoice is the only real competitor to Dragon NaturallySpeaking in the general business market. http://www-3.ibm.com/software/speech/
In the fast-changing world of technology, we expect improvement every year. IBM ViaVoice did some catching up recently. Release 9 now works with the Windows XP operating system. That upgrade is important because Windows XP and Windows 2000 work much more reliably than Windows 95, 98, or ME. It is also important because of the questionable quality of the speech recognition technology included in Windows XP.
Unfortunately, some annoyances still plague ViaVoice. I find it disappointing that a few have survived upgrade after upgrade. ViaVoice achieves the high accuracy essential to success. But effective speech recognition software must be more than accurate; it must be smart and helpful in punctuating, formatting and correcting your documents. In these areas, IBM ViaVoice falls well short of Dragon NaturallySpeaking.
IBM has done a nice job of extending the feature set of ViaVoice. Unlike NaturallySpeaking, ViaVoice is available not only for various Windows versions, but also for computers running Apple and Linux operating systems. Despite these advances, we rank ViaVoice behind NaturallySpeaking because of annoyances that interfere with the productive creation of documents.
Installation and Setup
ViaVoice Software
Installing IBM ViaVoice software took ten minutes and went smoothly. It required the usual steps: Enter your name and company, fill in a serial number, choose an installation folder, and register the product. Like other IBM software products, ViaVoice loaded an enormous number of files, 802, and took up 170 MB on the hard disk. Thankfully it added only three entries to the Windows registry. A reboot was required to activate ViaVoice.
Hardware Setup
When you first open ViaVoice, a User Wizard begins a multi-step process for setting up the program and creating “voice model” that it uses to recognize what you say. First you choose sound input and output devices from those installed on your system. Wizard windows walk you through setting up the microphone, including positioning it, testing for room noise and testing the recording level.
In a previous draft of these materials, I stopped dictating the document at this point. Unfortunately, ViaVoice repeatedly dropped letters from dictated words. This problem seemed to be specific to Microsoft Word 2000. After spending an hour on the phone with a committed but exasperated technical support person, she stated that the only solution for the problem would be to do further voice training to improve the voices recognition accuracy. That explanation was incorrect. Speech recognition software is designed so that it can only spell words the way they are spelled in its dictionary. For example, it cannot spell the word "receive" without the letter "i." But that is exactly the sort of error that ViaVoice was making.
Creating A Voice Model
Speech recognition software needs to adjust to your pronunciation and dialect. Surprisingly, it can manage wide individual variations. To get started, you need to spend 10 to 15 minutes reading a story while ViaVoice records your voice. ViaVoice then needs five to 20 minutes to process the results. Reading a second story for 25 to 35 minutes improves ViaVoice's accuracy. It needs 20 to 45 minutes to process the second story after you finish reading it aloud. In my view, IBM made excellent story choices, Treasure Island and a ghost story by Mark Twain. Part of the process involves reading some strange, fun sentences to assist ViaVoice in identifying related sounds. For example: “Loyal Lloyd employs alloys for exploit, and uses a scale to measure his treasure.”
§ User Wizard Tips:
During the creation of a voice model, User Wizard halted a few times on words that it did not recognize. Repeating the word usually got the wizard going again, but sometimes it repeatedly beeped despite my attempts to pronounce the word it was stuck on.
To work around this problem, click the Back button and then click on the story again. You will be returned to a spot near where the wizard halted and then you can continue.
Since continuous reading can be tiring, it is good that the wizard allows you to pause at any point - mid-sentence or not. If the phone rings, you can click on a pause button so that the wizard won't be confused by what you say. The "Click to Resume" button gets you going again.
IBM ViaVoice Documentation
IBM ViaVoice comes with a Quick Reference Guide divided into 11 sections. Relating to navigation are:
· Cursor Movement
· Desktop Navigation
· Internet Navigation
These sections are not intended to be comprehensive, but rather list the most frequently used commands. For example, 10 commands are listed under Cursor Movement, covering movement by word, line, page and beginning and end of document.
In addition to the navigation functions that duplicate the use of the cursor arrows, Home, End, Page Up and Page Down keys, speech recognition programs need to duplicate the mouse user’s ability to directly select a word. ViaVoice offers this capability with the “Select <text>” command and the “Select this” command.
“Select <text>” should move
the cursor to a previous
occurrence of the one or more words spoke by the user after saying,
“Select.”
In practice, this function may prove problematic. The user must pause
briefly
after saying, “Select.” Speaking too quickly caused
ViaVoice to type the word
“Select” and the <text>. Another problem is that the
ViaVoice often jumps
to a wrong word, and then seems to balk at moving from that word in
response to
further “Select” commands. Finally, there is the
unavoidable, occasional
problem that the word you want to select and ones that sounds like it
occur in
multiple places in the preceding text. ViaVoice lets you move from a
false hit
to the next occurrence by saying, “Try Again.” That moves
the selection
highlighting to the next occurrence of the word, but does not help if
the word
you really want is a homonym rather than another literal occurrence of
the
currently selected word.
Using Help
ViaVoice comes with excellent online help tools. Help screens are accessible using voice commands. “What can I say?” is the command you use to find out your options. You can further narrow the Help that will be displayed by saying, for example: “What can I say for Cursor Movement?”
Because of the broad set of commands, it is important for users to master the use of Help so that they won’t waste time finding new commands they need.
The complete ViaVoice documentation is available as an Adobe Acrobat PDF file that can be copied to the hard disk as a part of installing ViaVoice.
Formatting
Though the demands of formatting a legal brief are heavy, even a relatively short letter may contain italics, special capitalization, indented paragraphs and a list or table. ViaVoice automates part of the process of formatting, capitalizing the first letter of each sentence, putting a space after each period, and capitalizing a surprising variety of proper nouns that it recognizes. But much of the formatting is left up to the author and microphone.
Simply to capitalize a name such as “Drew” requires that the user say: “Capitalize on drew capitalize off.” Inserting paragraphs and line breaks is easier. Just say, “New line” or “New paragraph.”
A new feature available in ViaVoice is Natural Commands, which are available in MS Word, MS Excel, and MS Outlook. You need not say a command in precisely the right order for it to work. Natural Commands are mentioned below in Special Features.
Correction
“Scratch that” becomes an important part of a speech recognition user’s vocabulary. It erases whatever ViaVoice just typed and lets the user try again. But overuse of “Scratch that” will slow down the process of ViaVoice adapting to an individual’s voice and pronunciations. “Correct that” is the command ViaVoice needs to hear in order to improve its accuracy. This command is discussed further, below.
ViaVoice Correction Window
ViaVoice offers a good method for entering words with unusual spellings. Say “Spell mode,” then say each letter of the word continuously. When done, say “Return” or “Cancel” to return to normal dictation mode.
Whether the user can quickly and accurately make corrections may well determine whether the user will persist in using the product and will realize a true increase in efficiency. This aspect of using speech recognition software does not necessarily come quickly or easily. So here is another area where skilled instruction can make the difference between success and failure.
Speech File Building
Though ViaVoice is surprising accurate out of the box, individual speech files are used to improve its accuracy. Speech files are individual to each user. They are started during the initial “break-in” process during which the user reads passages from a story. They are refined as corrections are made to misrecognized words using the Correction window. That is how ViaVoice learns to recognize words accurately.
Correction By User
As a user dictates new documents at a computer, the correction window pops up in response to the command, “Correct this.” ViaVoice presents a quick list of the most probable alternatives to the incorrect word. Choosing one is as simple as saying, “Pick 3,” to pick the third word on the list.
If the word you want does not appear in the correction list, you can try re-dictating. Otherwise, you must resort to the keyboard to type in the word. Surprising, ViaVoice does not have a “Spell Mode” that would allow you to spell out the word in the Correction window. It has this mode outside the window. Dragon NaturallySpeaking seems to do a better job allowing re-dictation within the Correction window and does allow the user to spell out a word in that window.
Correction By Assistant
ViaVoice lost a big advantage it had over Dragon NaturallySpeaking when Dragon added the option for storing voice recordings right with the text version of a dictated document. This feature, now in both IBM ViaVoice and Dragon NaturallySpeaking Preferred, permits an assistant more power and flexibility in working with a dictated document.
Rather than having a busy attorney lose billable hours on the rather tedious process of correcting misrecognized words, an assistant can perform much of that function.
First, the attorney dictates a document, saving the document and associated voice recording file on the network. Next, the assistant, who also has ViaVoice, proofreads the document, stopping at misrecognized words and correcting them with the Correction window. In order to determine accurately which word the attorney wanted, the assistant can replay the recording of the attorney’s voice saying the word in question. The assistant must then make sure that the improved speech files for that attorney are copied back to the computer that the attorney uses for speech recognition. This process results in increasing ViaVoice accuracy while sparing the attorney from the time-consuming extended break-in period.
Special Word Lists
To accelerate the process of improving the accuracy of ViaVoice, the user can draw on any of several resources to build the ViaVoice dictionary of words it recognizes. A special legal version is available at extra cost. A built-in feature allows the user to add up to 64,000 words to ViaVoice’s personal vocabulary.
§ Analyze Documents
From Tools / Analyze My Documents, the user can point ViaVoice at a collection of his or her documents. ViaVoice will scan through the documents, identifying words that do not yet exist in its vocabulary. The user then has the opportunity to train ViaVoice to recognize these words.
§ Find New Words
Instead of using the Correction Window to correct text as you dictate, the user can make corrections with the keyboard during or after dictation. After the text is corrected, the user can have ViaVoice analyze the document to find new words or phrases that need to be trained.
Special Features of ViaVoice
Natural Commands
For MS Word, MS Excel and MS Outlook (from Office 97 and Office 2000), ViaVoice supports natural commands for formatting documents. This feature is a big step forward. The commands needed to format documents are so numerous that it is difficult even for very quick learners to master the whole set of literal commands. Natural commands give the user flexibility in the words used and the order in which they are used to communicate commands.
Natural commands should be preceded with the word “Computer” so that they are not interpreted as ordinary dictation. (The word “Computer” will be recognized as a command if the user pauses briefly before and after saying the word.)
For example: “Computer, move to top of page.”
Without Natural Commands, the user would have to dictate, “Move to beginning of page.” The difference may not seem large, but across a wide set of commands, it measurably reduces frustration.
Voice Recordings
ViaVoice has the option to save the audio portion of a dictated document in a Session file. These files take up a good deal of hard disk space, but disk space has become inexpensive. Session files allow attorneys to become even more efficient during the extended break-in period and afterwards by relying on an assistant to handle the correction of misrecognized words. An assistant can refer to both the text and the sound files when proofing a document dictated by an attorney using ViaVoice.
Macros
Users can create special phrases, such as “inside-address,” that, when dictated, will result in the insertion of fully formatted boilerplate text. These are not difficult to create and can become quite involved. The challenge is to organize and document them well so that it will be easy to use them on a day-to-day basis. The macro command itself must be recorded by each user, but the contents of a macro do not have to be recreated. They can be exported from one user to another.
Installation and Setup
Required Hardware
For Dragon NaturallySpeaking Version 5, you can get by with a computer that is a year or two out-of-date. But for Version 6, we recommend a Pentium 4 or advanced Athlon chip and 512 MB of RAM.
On a PC equipped with 256 MB of RAM and a Pentium III 750 MHz chip running Windows 2000, this writer experienced slowdowns when using Version 6 with MS Word XP and Time Matters.
Dragon Software
Installing Dragon NaturallySpeaking Version 6 was simple. Insert the CD, click Next a number of times, fill in your name and registration information. It installed 396 files filling 264 MB. Version 5 required a lot less space, installing 225 files taking up 97 MB of space, far less than IBM ViaVoice. Surprisingly, it made no entries in the Windows registry.
Hardware Setup
Dragon has you read out loud twice for about 15 seconds each time to check microphone volume and signal-to-noise ratio.
Training
Mastering any speech recognition requires an unexpected amount of training. The software needs to be trained to recognize the user's voice accurately. The user must develop dictation skills and master essentially two new languages: screen navigation and document formatting.
The process of training Dragon to recognize your particular speech begins with reading to the computer for about five minutes. It is surprising how accurate the software becomes in such a short time. However, to make it truly usable, it is important to continue on and read another, longer section to the computer. With each new release, Dragon offers more interesting choices:
o Talking to your Computer (includes Kennedy Address)
o Kennedy's Inaugural Address
o Success is a Journey
o Dogbert's Top Secret Management Handbook
o 3001: The Final Odyssey
o Stories Written by Children
o Alice's Adventures in Wonderland
o Charlie and the Great Glass Elevator
o The Captain of Battery Park
You read through the selection so that Dragon can get used to the sound of your voice and match what you say with the words in its dictionary. (I recommend "Success Is a Journey.")
Next Steps
Showing its maturity, Dragon NaturallySpeaking offers three choices tailored to users with varying levels of experience.
· Start the Tutorial
· See What’s New
· Begin Dictating
The tutorial provides a great blend of a helpful audio track, animated demos, hand and live interactive practice. Starting with the tutorial is strongly recommended.
An invaluable aid in learning the program is the Quick Start pamphlet. Because it is short and full of helpful color diagrams, users are drawn to it. In addition, it has a flip-out Command Quick Reference listing its many commands in intelligent groupings.
Special Features of Dragon NaturallySpeaking
Fast Correction Process
The process for correcting recognition mistakes flows more smoothly than the ViaVoice process. Dragon also makes it easy to improve the speech files so that future recognition mistakes will be avoided. The entire process is easily controlled by voice.
Easy Formatting Commands
Dragon shines at formatting text the way we expect it to be formatted. There is even an option for putting either one or two spaces after a period.
Navigation Commands
Our experience with Dragon’s navigation commands was very positive. For example, both the phrases “move to end of line” and “go to end of line” had the desired effect.
Dictation Shortcuts
The $69.95 version of Dragon NaturallySpeaking Standard Version 5 (not available as a Version 6 product) allows the creation of one-liner shortcuts such as your e-mail address or firm name. The $199 Dragon NaturallySpeaking Preferred Version 6 supports the insertion of boilerplate paragraphs, full addresses and phrases.
Hardware
The wrong sound cards, microphones, and amount of RAM are responsible for a surprising number of speech recognition project failures. My thinking on the best hardware has changed based on the experiences of speech recognition experts with the latest software and hardware.
Microphones – The Rules Have Changed
I used to recommend the use of a USB microphone in all circumstances. This recommendation was supported by the horror stories that have come out of the use of speech recognition software on electronically noisy laptops and even desktop computers. A USB microphone is still recommended as a fall-back if the user is unsuccessful using a good microphone and sound card.
Latency is a reason to avoid USB microphones if possible. Latency can cause the first word or two of dictation to be lost each time the user resumes speaking. It can also cause delays in the transcription of the user’s words.
Another factor enters into the choice of a microphone. When you train your speech recognition software, it saves customized information about your voice in user files (or what's IBM calls a "voice model").
If you use a USB microphone, these user files are "locked" to your microphone. You could transfer the user files to a different computer and still be able to use them so long as you continue to use your original USB microphone. While they are not truly “locked” to that particular microphone, the odds are you will only get good results if you stay with that microphone.
However, if you use a normal microphone, your user files are "locked" to both your microphone and your sound card. To switch to another computer and still use your user files, you also need to use the same or an identical sound card on the new computer.
The process of creating a good set of the user files is especially time-consuming. That is why it is important either to be able to reuse them if you're going to change computers or to be able to reconstruct them efficiently.
Both Dragon NaturallySpeaking and IBM ViaVoice allow you to train the software to recognize the new list of words. This feature facilitates the process of training a new installation of the software on another computer. With both programs, you can create a text file containing all of the individual words which you added to your user files. Before moving from one computer to another, you can save this list of words.
After installing speech recognition software on the new computer, you can efficiently train the software to recognize all of words that you added on your old computer.
Microphone placement is also important. It is best to use a headset so that you can position the microphone consistently close to your mouth and out of your air stream. It is convenient to be able to rotate the microphone away from your mouth and back so that you can drink something without removing the headset.
Sound Card
A high quality, compatible sound card is important for success with speech recognition. It is unfortunate how many users have become completely disillusioned about speech recognition because of an acoustic problem. Take the time to confirm that the sound card in your computer is approved by the vendor of your speech recognition software. In most cases, a SoundBlaster Live card will be compatible and produce good results.
If you cannot change the sound card in your system, and you do not get good results during the initial hardware testing phase of installing your software, spend about $70 on a USB headset microphone. It will bypass the sound card and some of the noisy circuitry in your computer. That may solve the problem.
Processor
Consider a 750 MHz Pentium III as a decent processor for effective speech recognition at this writing. The faster, the better, because the recommended minimum increases each year. If you're buying new computer, choose one with a Pentium 4 late-model Athlon chip. You don't need the very fastest chip on the market, however.
RAM
Consider 256 MB of RAM as a bare minimum. The whole point is to become more efficient. Why save a few dollars, and then find yourself slowed way down.
By investing in 512 MB of RAM, you allow yourself to have multiple programs open and still be able to use speech recognition efficiently.
Hand-held Dictation Unit
The selection of products in the hand-held dictation unit niche is rapidly changing. For anyone considering the purchase of such a unit, I suggest you try out the hand controls in a store. You will be using them a lot, so you will want them to work well for you.
User Training
With most software programs, the user needs to learn one new approach to working with information. To learn the Web, the user masters hyperlinks, Web addresses, forward and back buttons, and maybe some search engine rules. To use a spreadsheet program, the user learns about columns, rows, formulas, sorting and perhaps a bit about graphs. Often skills learned in one program carry over to another.
To become quite comfortable with speech recognition software, a new user must move up a number of learning curves simultaneously. Skills carry over from the world of word processing, but many of them have very unfamiliar new twists.
Speaking Naturally
Speaking naturally does not come naturally to new users of the speech recognition software. If left to our own devices, we tend to over-enunciate, slow down, speak more distinctly, and change our pronunciations of words when speech recognition software does not perfectly recognize what we say. Each of these behaviors is self-defeating. Speaking naturally is the goal.
To learn the effective use of speech recognition software, new users need the help of experienced instructors who will listen to them, helping them to avoid problematic adjustments. Besides teaching users to speak truly naturally, instructors have a number of other important skills to develop in their students.
The hardest practice to master is dictating everything in your normal voice. You will be tempted to alter your voice, subtly or not, in a misguided effort to prevent the software from making mistakes. Ironically, mistakes are good! This sequence makes the software better: You say something normally; the software recognizes it incorrectly; then you correct the mistake. Going through this sequence many times is an important part of the process of training speech recognition software to recognize your spoken words.
Dictation Skills
Twenty-five years ago, it was common for new lawyers to learn to dictate documents. These days, many lawyers prefer to draft their own documents using the keyboard and have not developed dictation skills. The ability to speak into a microphone and create coherent documents is not something one learns overnight. However, dictation skill is important to success with speech recognition software.
Punctuation
Attorneys experienced with dictating may assume that lawyers with more than a few years of experience all know how to dictate. Currently, it is safer to assume that they are experienced typists rather than experienced with dictating equipment. That means the process of inserting punctuation verbally is a new skill that most users need to learn in order to effectively use the speech recognition software. Commands for punctuation marks like "period," "comma," and "exclamation point" are easy to remember, but hard to remember to insert consistently speaking into a microphone.
Navigating within and among Programs
You are probably used to moving the mouse around, but to dictate rapidly with speech recognition software, you are better off using voice commands to navigate around our documents. To do so, you need to memorize a separate vocabulary and also get used to pausing briefly before and after dictating a navigation command.
Proofreading
For all dictated documents that go outside the law office, weigh very carefully the importance of having a second set of human eyes proofread them. Try as you will, if you dictated a document, you will not find all of the words that speech recognition software has misrecognized.
Misrecognition errors are insidious. They don’t show up in a spelling-checker, since speech recognition software cannot make classic typos; it can only use words that are in or have been added to its dictionary. The erroneous words will be especially hard to spot, since they are spelled correctly and “sound like” the correct word. Misrecognized words that you don’t catch can be very embarrassing. Rely on another person to proofread anything important.
Compatibility with Specialized Programs
Speech recognition software varies in its ability to work with specialized programs. Though it may contain powerful features when working in MS Word, Corel WordPerfect, or MS Internet Explorer, speech recognition software may lose import navigation and even correction commands when used to dictate into some non-mainstream programs.
If your office enters a significant amount of text into a particular program, consider testing it with a speech recognition product before launching a project. You may want to consult with a speech recognition expert to see if the two programs can be tweaked to work well together.
Training
Devote sufficient time and resources to master the three learning curves:
1. Basic dictation skills
2. Formatting language
3. Navigation and correction language
Get to know and use the documentation, tutorials and help screens.
Lower your initial expectations. Try the most appropriate writing tasks first: narrative internal notes, rough drafts, internal E-mails. Speech recognition pays big dividends, but it takes time to master it. Stick with it.
Techniques
Speak naturally.
Correct misrecognized words with the correction tool.
Use a grammar-checker.
Use a proofreader.
Backup
Be sure to back up your priceless speech files and customized, personal vocabulary to insure against losing hours of your valuable time. Speech recognition stores these files on the hard drive of your computer, not the network. If your hard disk fails or your software is deleted, your use of speech recognition may grind to a halt.
Dragon NaturallySpeaking Version 5 does not have a procedure for backing up your speech files to tape or to another drive. Therefore, you need to go through a two-stage process to protect them. First, back up the User to your computer’s hard disk. Second, use a disk backup utility program or Windows Explorer to copy the files onto another disk or tape.
1. User Backup
a) Open NaturallySpeaking with the User you want to back up.
b) On the NaturallySpeaking menu, go to Advanced | Backup User.
2. Backup the Software
Using Windows Explorer, find the folder for the Dragon NaturallySpeaking software files. Usually it is on the C: drive in the Program Files folder. Copy the User folder and subfolders to another disk or tape. A backup program or Zip program like WinZip, http://www.winzip.com , can speed up this process and save space.
If you need to restore from this backup, you need to reinstall the software from the CD-ROM and create a User with a name different from the name of the User you backed up. By copying the backed up User folder into the proper location in the newly installed software folders, you should be able to Restore a User and get your speech files working again.
In Dragon NaturallySpeaking Version 6, you can Export a User to backup your speech files:
1. Go to Dragon Bar | NaturallySpeaking menu | Save User Files
2. Now go to NaturallySpeaking menu | Export
3. Use the Browse for Folder window to choose the location for the files.
Conclusion
Does speech recognition really work? It depends. If you approach it skeptically without committing the necessary time and resources and without an understanding of the obstacles, no, it does not work. If you purchase the right equipment, receive competent training, persevere, and understand what is required to make it work, yes it can.
Dragon NaturallySpeaking (as of January, 2002)
At PC Connection - http://www.pcconnection.com
Dragon NaturallySpeaking Legal Solutions 6 (not in stock) – Ret. $995 $779.95
Dragon NaturallySpeaking Professional Version 6 – Ret. $695 $569.95
Dragon NaturallySpeaking Preferred Version 6 – Ret. $199 $164.95
Corel WordPerfect Office 2002 Pro Upgrade (with Dragon V. 5) $249 $219.95
At CNET Shopper – http://shopper.cnet.com
Dragon NaturallySpeaking Standard V. 5 (old version) $69.95
Dragon NaturallySpeaking Essentials V. 5 (old version) $49.32
IBM ViaVoice
At PC Connection - http://www.pcconnection.com
ViaVoice Pro USB 9.0 – Ret. $219 $189.95
ViaVoice Advanced 9.0 – Ret. $105 ($40 compet. rebate til 7/6/02) $94.95
ViaVoice Standard 9.0 – Ret. $ 57 $54.95
ViaVoice Personal 9.0 – Ret. $29 ($20 compet. rebate til 7/6/02) $27.95
ViaVoice Legal Vocabulary – Ret. $142.00
Open Directory Project, speech recognition topic: http://dmoz.org/Computers/Speech_Technology/
Freedom of Speech
National specialists in speech recognition technology and training
Web: http://www.freedomofspeech.com
Articles on speech recognition:
http://www.wellslegaltech.com/articles.htm
