Chapter 1
Knowing What to Expect
In This Chapter
Clarifying what Dragon Professional Individual can do
Figuring out what Dragon Professional Individual can’t do
Selecting the right Dragon product
Voice recognition is used in places like cars, hospitals, and legal offices. Yet, some people are still skeptical about software that enables you to dictate to your computer and get a transcription of what you said. People think it’s very cool, but they secretly wonder if it really works.
It works. (And it is really cool.) Right out of the box, today’s Dragon Professional Individual reports up to 99 percent accuracy. I bet that’s a score you’d like for your own personal output. Well then, read this book and dive right in. You’ll be rewarded with higher productivity and hands-free computing.
Sections of this book were written by dictating them into Dragon Professional Individual. It was a lot of fun, and I predict that you will also find Dragon Professional Individual to be useful and fun — if you approach it with the appropriate expectations.
Clarifying What Dragon Professional Individual Can Do for You
Something about dictating to a computer awakens all kinds of unrealistic expectations in people. If you expect it to serve you breakfast in bed, you’re out of luck. I didn’t write this book by saying, “Computer, write a book about Dragon Professional Individual.” I had to dictate it word for word, just as I would have had to type it word for word if I didn’t have Dragon Professional Individual.
So what are realistic expectations? Think of Dragon Professional Individual the way that you think about your keyboard and mouse. It’s an input device for your computer, not a brain transplant. It doesn’t add any new capabilities to your computer beyond deciphering your spoken words into text or ordinary PC commands. If you say, “Go make me a sandwich,” Dragon Professional Individual will dutifully type “go make me a sandwich” into whatever word-processing application happens to be open.
Just because your computer can understand what you say, don’t expect it to understand what you mean. It’s still just a computer, you know.
Here are five specific things you can expect to do with Dragon Professional Individual, and where to look for more details about how to do them:
- Browse the web. If you use Internet Explorer (IE) (or Chrome or Firefox) and Dragon Professional Individual together, you can cruise around the web without ever touching your keyboard or mouse. Pick a website from your Favorites menu, follow a link from one web page to another, or dictate a URL (web address) into the Address box, leaving your hands in your lap the whole time. See Chapter 13 for details.
- Control your applications. If you see the name on a menu, you can say click and the name and watch it happen — not just in Dragon Professional Individual but in your other applications as well. If your email program has a Check Mail command on its menu, then you can check your email by saying a few words. Anything that your spreadsheet has on a menu becomes a voice command you can use. Ditto for hotkeys: If pressing some combination of keys causes an application to do something you want, just tell Dragon Professional Individual to press those keys. See Part II.
- Control your desktop. Applications will start running just because you tell them to. Use your voice to open and close windows, switch from one open window to another, and drag and drop stuff from here to there. See Chapter 15.
- Dictate into a digital recorder and let Dragon Professional Individual transcribe it later. You need Dragon Professional Individual and a digital (or very good analog) recorder. See Chapter 11.
- Write documents. Dragon Professional Individual is darn good at helping you write documents. You talk, and it types. If you don’t like what you said (or what Dragon Professional Individual typed), tell Dragon Professional Individual to go back and change it. You can give vocal instructions to make elements bold, italic, large, small, or set in a particular font. Chapters 3, 4, 5, and 6 explain what you need to know to write documents in the Dragon Professional Individual DragonPad itself. If you want to dictate into Microsoft Word or Corel WordPerfect, see Chapter 9. For all other applications, see Chapter 8.
Now, I happen to think that’s plenty to get excited about. I can make my own sandwiches, thank you.
Figuring Out What Dragon Professional Individual Can’t Do
Even with Dragon Professional Individual, your computer’s capability to understand English is more limited than what you can reasonably expect from a human. People use a very wide sense of context to figure out what other people are saying. We know, for instance, what the teen behind the counter at Burger King means when he asks, “Wonfryzat?” (That’s fast-food-employed teenspeak for “Do you want fries with that?”) We’d be completely confused if that same teenager walked up to us at a public library and asked, “Wonfryzat?”
Dragon Professional Individual figures things out from context, too, but only from the verbal context (and a fairly small verbal context at that). It knows that “two apples” and “too far” make more sense than “too apples” and “two far.” But two- to three-word context seems to be about the extent of the software’s powers. (I can’t say exactly how far it looks for context, because Nuance, the manufacturer, is understandably pretty hush-hush about the inner workings of Dragon Professional Individual.) It doesn’t understand the content of your document, so it can’t know that words like “Labradoodles” and “Morkies” are going to show up just because you’re talking about dogs.
However, Dragon does use context in its analysis. Dragon Professional Individual has collected millions of hours of dictation from customers and uses this data to better understand the language. A word receives a frequency score that shows how often the word appears and how often the word appears before or after other words. This data is then used to determine the best choice; for example, when you mention “too” or “two.”
Try to speak in slightly longer utterences. The more you say in one breath, the more data Dragon has. But be careful: Try to say too much at one time, and you will likely trail off or start to mumble as you lose concentration.
Consequently, you can’t expect Dragon Professional Individual to understand every form of speech that humans understand. In order to work well, it needs advantages like these:
Familiarity: Each person who dictates to Dragon Professional Individual can train it so that Dragon Professional Individual builds an individualized user model.
Even though you no longer have to train Dragon, it still creates a speaker-dependent profile. After the audio setup is complete, Dragon Professional Individual is already making it unique to you. That’s why you must always use your own profile.- Identification: Each time you start dictating, you need to identify yourself so that Dragon Professional Individual can load the right user model.
- One user at a time: Dragon Professional Individual loads only one user model at a time, so it can’t transcribe a meeting during which several people talk, even if it has user models for all of them.
- Constant volume: You can’t plunk a microphone down in the middle of the room and then pace around while you dictate.
- Use a good, Nuance-approved microphone. You can find a list at
http://support.nuance.com/compatibility. Position the microphone the same way every time or sit in front of your computer. Try to stay at the same distance from your PC’s internal array microphone. Don’t mumble or let your voice trail off.
Dragon does a pretty good job with accents, as long as you’re consistent.
- Use a good, Nuance-approved microphone. You can find a list at
- Reasonable background noise: Humans may be able to understand you when your favorite drummer is blasting away on your speakers or the blow dryer is on. They may be reading your lips at least part of the time, and they can guess that you’re probably saying, “Turn that thing down!” Dragon Professional Individual lacks in the lip-reading department, as well as in the capability to make obvious situational deductions.
- Reasonable enunciation: You don’t have to start practicing “Moses supposes his toeses are roses,” but you do need to realize that Dragon Professional Individual can’t transcribe sounds that you don’t make. See Chapter 16 for an in-depth discussion of this issue.
- Standard turn-of-the-millennium English prose: If you want to be the next James Joyce, stick to typing. You can have some fun by trying to transcribe Shakespeare or things written in other languages (I had fun in Chapter 25), but it isn’t going to work very well (unless you do some really extensive training). On the other hand, Dragon Professional Individual is just the thing for writing books, blog posts, and reports.
Letting someone else use your profile will negatively affect your accuracy.
Selecting the Right Dragon Product
Dragon doesn’t have a single product; it’s a family of products. And like most families, some members are richer than others. Depending on the features you want, you can pay a hefty price for software. You get what you pay for.
In spite of its members’ socioeconomic differences, this family gets along pretty well. All the products are based on the same underlying voice recognition system, so they create the same kinds of user files. This fact has two consequences for you as a user:
- All the products are about equally accurate at transcribing your speech. However, the Legal version has specific legal terms included, and the language models are more tuned to expect legal phrases. The same idea holds true for the Medical version.
Upgrading to a better version is easy.
You can start out with the inexpensive Dragon NaturallySpeaking Home edition, test whether you like this whole idea of dictation, and then move up to a full-featured version without having to go through training all over again.
Which edition is best for you depends on why you’re interested in Dragon in the first place. Are you a poor typist who wants to be able to create documents more quickly? A good typist who is starting to worry about carpal tunnel syndrome? A person who can’t use a mouse or keyboard at all? A busy executive who wants to dictate into a recorder rather than sit in front of a monitor? Is price an important factor to you? Do you need Dragon to recognize a large, specialized vocabulary? Do you want to create macros that enable you to dictate directly into your company’s special forms?
The more features you want, the more you should expect to pay.
Expanding the use of speech recognition
Speech recognition software is entrenched in many private sector industries. Dragon serves several industries, including the following:
- Financial: Dragon helps financial people manage their paperwork and meet compliance requirements.
- Legal and medical: Transcription and documentation play a major role in keeping things moving in the legal and medical fields. Dragon significantly cuts the time needed to produce various documents.
- Insurance: This one is self-explanatory. Anything that cuts down on paperwork in the insurance industry is clearly a public service.
The public sector uses Dragon as follows:
- Education: It is well documented that Dragon can help level the playing field for students who face learning challenges. Teachers can provide better learning experiences to all their students.
- Accessibility: Dragon makes a major contribution to people who are challenged by the use of a keyboard or mouse. The software provides access to the web and opens up the world to people who might otherwise be denied digital access.
- Public safety: Dragon’s capability to save time on paperwork frees up law enforcement professionals to do the work that keeps us safe.
The latest generation of the Dragon family
The current generation of Dragon products was released in the second half of 2015. In addition to the usual bug fixes and incremental improvements that you expect in a new version of an application, Nuance is splitting its next version of Dragon into Dragon Professional Individual and Dragon Professional Group.
Dragon Professional Individual and Professional Group still have the same great features, including the following:
- Up to 99 percent accuracy: Every facet of Dragon Professional Individual works faster by cutting down on the time required for the program to recognize dictation and produce output.
- Fast response time: Response to commands is fast and makes dictating less about stopping and starting. You can pay attention to longer phrases with pauses in between.
- Shortcuts for common commands: Nuance has anticipated many of the common commands that you want to use and has created shortcuts for them.
- No training to set up: You don’t have to spend time reading documents. Nuance has made this version a five-minute task.
- The well-designed DragonBar: Using the DragonBar is easier than ever before. It’s streamlined and can be collapsed or opened at the click of a mouse. No extended menu needed, either.
Here are some of the new features in Dragon Professional Individual:
- Advanced custom commands: You can create and import powerful commands to automate tasks and can also easily insert variable fields in auto-text commands.
- The ability to transcribe someone else’s voice from an audio file: Another exciting new feature is the ability to transcribe another voice without requiring the speaker to be personally present to train a profile.
- Improved Help to get a new user up to speed and running quickly: In-context Help with “What can I say?” that gives you top commands to say depending on which application you are in, enhanced Tutorial, and enhanced online Help support.
The new Dragon Professional Group product is aimed at productivity for the enterprise:
- Enabling and managing multiple desktops with Dragon in an enterprise using administrative tools as well as the option to connect with the Nuance User Management Center, for centralized administration
- Volume licensing with maintenance and support options
Nuance is also introducing Dragon Anywhere. This is a new application available for iOS and Android devices. You can multiply your productivity by dictating to your mobile devices, and the following features are available:
- Edit and format right on your mobile device: Enjoy the ability to work right on your device to get your document in shape.
- No limit on speaking length: You can talk as long as you want to get the job done to your satisfaction.
Here are the some of the other Dragon NaturallySpeaking products with a few comments about their features:
- Dragon Home: This entry-level edition is perfect for people who hate to type. Since the other editions have more powerful features better suited for work, it is recommended for use at home. It is as accurate as the more expensive editions, enables control of the Windows desktop, includes a Dictation Box for dictating into other applications, and enables you to browse the web by voice. The Home version includes Full Text Control for a number of applications and some Natural Language Commands for Word, WordPerfect, and OpenOffice Writer. It doesn’t support Full Text Control in Excel or playback of your own voice for corrections. The Home edition is perfect if you’re planning to dictate only the first draft of documents, which you then polish using a mouse and keyboard. This version probably isn’t the best choice for people with physical disabilities.
- DragonPremium: Premium includes all the Home edition’s features, plus a few extras. It’s also recommended for home use. It enables you to select a piece of your document and play back your own dictation, a great feature when you’re trying to correct a mistake that either you or Dragon made 20 minutes ago. It also opens the possibility of dictating into a recorder (including a smartphone) and letting Dragon transcribe it later. See Chapter 11.
Dragon Legal and Dragon Medical Practice Edition: At heart, these two editions begin with the Professional edition, but Nuance has done some of the work that I describe about the office geek in the preceding bullet.
- Medical edition: Comes out of the box knowing the names of obscure diseases, body parts, and pharmaceuticals. The Medical versions can be seen as their own family of products. There are versions for different types of healthcare providers and organizations. It is important to know that the Medical versions of Dragon are the only versions that will allow you to dictate into an electronic medical report (EMR or EHR) application.
- Legal edition: Knows amicus curiae, habeas corpus, and a bunch of other Latin legal terminology that would make the Professional edition throw up its proverbial hands.
Nuance may be changing the name of Dragon Legal 13 and Dragon Premium 13 in the upcoming future. At the time of this writing, it remains the same.- Dragon for the Mac: I cover the Dragon Windows products in this book, but Nuance also has a collection of products for the Mac, including Dragon for Mac and Dragon Dictate Medical for Mac. If you know some Mac users, tell them to check these out. (For use with mobile devices, including the iPhone, iPod, or iPad, see Chapter 14.)
In addition to these off-the-shelf products, you can also have Dragon Professional Group installed on your office network. This corporate option goes beyond the scope of what I cover in this book. If you’re interested in this option, contact Nuance directly. Training programs for your staff are also available.
Understanding Speech Recognition in Dragon
Nuance has eliminated the training during set-up. But if you really want to make Dragon Professional Individual blazing fast, you should train it to understand you and the special words and phrases you use. So why does Dragon Professional Individual need to be customized before it understands your speech? The simple answer is that speech recognition is probably one of the hardest things your computer does. Humans may not think speech recognition is hard, but that’s because they are good at it. LeBron James probably has trouble understanding why the rest of us think it’s so hard to dunk a basketball.
This section explains why deciphering speech is hard for computers and how training Dragon Professional Individual can overcome these difficulties. I hope that understanding these issues will give you confidence that the extra effort is worth it.
Dragon Professional Individual comes out of the box not knowing anything about you. It has to work as well for a baritone with a Scottish accent as for a mezzo-soprano with a slight lisp. It needs time to figure out how you talk.
Training continues for as long as you keep using Dragon Professional Individual. It makes mistakes, you correct them, and it learns. That’s the process. It gets better and better the more frequently you use it.
The exact error rate depends on many factors: how fast your computer is, how much memory it has, how good your microphone is, how quiet the environment is, how well you speak, what sound card your computer has, and so on.
Dragon Professional Individual is up to 99 percent accurate out of the box and it gets better as long as you keep correcting it. Don’t be lazy.
What’s so hard about recognizing speech, anyway?
If three-year-olds can recognize and understand speech (other than the phrase “go to bed”), why is it so hard for computers? Aren’t computers supposed to be smart?
Well, yes and no. Computers are very smart when it comes to brain-straining activities like playing chess and filling out tax returns, so you may think they’d be whizzes at “simple” activities like recognizing faces or understanding speech. But after about 50 years of trying to make computers do these simple things, programmers have come to the conclusion that a skill isn’t simple just because humans master it easily. In fact, our brains and eyes and ears are chock-full of sophisticated sensing and processing equipment that still runs rings around anything we can design in silicon and metal.
We humans think it’s simple to understand speech because all the really hard work is done before we become conscious of it. To us, it seems as if English words just pop into our heads as soon as people open their mouths. The unconscious (or preconscious) nature of the process makes it doubly hard for computer programmers to mimic. If we don’t know exactly what we’re doing or how we do it, how can we tell computers how to do it?
To get an idea of why computers have such trouble with speech, think about something that they’re very good at recognizing and understanding: touch-tone phone numbers. Those blips and bloops on the phone lines are much more meaningful to computers than they are to people. Several important features make the phone tones an easy language for computers, as I discuss in the following list. English, on the other hand, is completely different:
- The touch-tone “vocabulary” has only 12 “words” in it. After you know the tones for the ten digits plus * and #, you’re in. English, on the other hand, has hundreds of thousands of words.
- None of the words sound the same. On the touch-tone phone, the “1” tone is distinctly different from the “7” tone. But English has homonyms, such as new and gnu, and near homonyms, like merrier and marry her. Sometimes entire sentences sound alike: “The sons raise meat” and “The sun’s rays meet,” for example.
- All “speakers” of the language say the words the same way. Push the 5 button on any phone, and you get exactly the same tone. But an elderly man and a 10-year-old girl use very different tones when they speak; and people from Great Britain, Canada, and the United States pronounce the same English words in very different ways.
- Context is meaningless. To the phone, a 1 is a 1 is a 1. How you interpret the tone doesn’t depend on the preceding number or the next number. But in written English, context is everything. It makes sense to “go to New York.” But it makes no sense to “go two New York” or “go too New York.”
What’s a computer to do?
In order to work effectively for you, a speech-recognition program like Dragon Professional Individual needs to combine four vastly different areas of knowledge. It needs to know a lot about speaking in general, about the spoken English language in general, about the way your voice sounds, and about your word-choice habits.
How Dragon Professional Individual knows about speech and English in general
Dragon Professional Individual gets its general knowledge from the folks at Nuance, some of whom have spent most of their adult lives analyzing how English is spoken. Dragon Professional Individual has been programmed to know in general what human voices sound like, how to model the characteristics of a given voice, the basic sounds that make up the English language, and the range of ways that different voices make those sounds. It has also been given a basic English vocabulary and some overall statistics about which words are likely to follow which other words. (For example, the word medical is more likely to be followed by miracle than by marigold.)
How Dragon Professional Individual learns about your voice
Dragon Professional Individual learns about your voice by listening to you. Dragon Professional Individual goes on learning about your voice every time you use it. When you correct a word or phrase that Dragon Professional Individual has guessed wrong, Dragon Professional Individual adjusts its settings to make the mistake less likely in the future.
Dragon learns even when you make keyboard edits or delete everything and start over, taking the net result of your dictation or typed text and using it to help improve its accuracy.
Dragon Professional Individual learns in two ways:
- The Language Model: When you make edits with your keyboard, Dragon will update your Language Model and better understand which words you use and when. However, Dragon Professional Individual will never add a word to your vocabulary unless you add it manually in the Vocabulary Editor or use the “Spell That” option to make your correction.
- The Acoustic Model: Dragon becomes more accurate by updating your Acoustic Model, which is how you sound and pronounce words. When you make corrections with your voice, Dragon updates both your Language Model and your Acoustic Model because it now has both the text and the audio associated with that text.
Although you can correct with your keyboard, Dragon becomes smarter when you correct with your voice. Either way, though, Dragon gets better!
How Dragon Professional Individual learns your word-choice habits
Dragon Professional Individual learns how you choose words if you choose to have emails or documents analyzed. It may seem as if Dragon Professional Individual is just learning how you say some unusual words. But, in fact, running this tool is worthwhile even if no new words are found, because Dragon Professional Individual analyzes how frequently you use common words and which words are likely to be used in combination.
Dragon Professional Individual comes out of the box knowing general facts about the frequency of English words, but having Dragon learn from emails or documents helps sharpen those models for your particular vocabulary.
For example, if you want to use Dragon Professional Individual to write a report, let it study your previous reports. Dragon Professional Individual will learn that the names of your colleagues appear much more frequently than they do in general English text. It is then much less likely to misinterpret your boss Johan’s name as John or yawn.
Onward to Customizing!
By enabling you to install Dragon Professional Individual, your computer has taken on one of the hardest tasks a PC ever faces. It needs your help. If you use it with patience and persistence, and if you gently but firmly correct your Dragon Professional Individual assistant whenever it makes a mistake, you’ll be rewarded with a computer that takes your verbal orders and transcribes your dictation without complaint (and even without a coffee break, unless you need one).