Category Archives: Speech Recognition

Tip: Link phrases and website paths


You’re using the Utter Command Site list utility to go directly to websites, e.g. “Twitter Site”. And you’re comfortable saying the numbers that appear next to links to get around websites, e.g. “11 Go”. What’s next?

Is there a place where you find yourself constantly using two link numbers in a row? Try speeding things up by saying them as one phrase. For instance, in Google documents, I say “7 Go” to drop-down the Insert menu and “84 Go” to choose Horizontal Line. After a few times you don’t have to look: say “7 Go 84 Go” to do it all at once.

Here’s another tip that starts with a riddle: how are the following two tasks connected?

1. Going directly to a website but not in your default browser

2. Emailing a website link to a friend

Answer: you can use the same command to do either one.

Say you’re in a browser that’s not your default browser, and you want to go to the Twitter website. Put the cursor in the address bar (“Go Address”). Then paste the path of any website that’s on your Site list by adding “Path” to whatever you’d normally say to go to the site, e.g. “Twitter Site Path”.

Same goes for when you want to drop a link into an e-mail message. If the site in question is on your Site list, there’s no need to go to the site and cut and paste — use the Path command to paste the Web address into your message.


Have you found a good application for double Link numbers? Tell me about them – reply here or let me know at info@ this website address.

Tip: Help on the NaturallySpeaking utilities


A few weeks ago the folks at Nuance posted a Dragon NaturallySpeaking 10 user workbook. It’s an excellent resource. It includes detailed instructions on NaturallySpeaking speech engine utilities that will make your speech experience better.

Here are my favorite parts:

The instructions for creating a user profile (page 1) explain important concepts like choosing the right dictation source. If you accidentally choose the wrong dictation source, your accuracy will not be as good.

The Vocabulary dialog box (page 8) allows you to add custom vocabulary including phrases, and import custom vocabulary from existing documents. I make sure my users have “Utter Command” and “Redstart Systems” as phrases. I have a usability complaint about the Vocabulary dialog box, however. It’s difficult to find in the menus because the menu name doesn’t match the dialog box name: NaturallySpeaking/Words/View-Edit. I think the label should be Vocabulary Editor instead.

The Formatting dialog box (page 23) allows you to control automatic formatting of special text like numbers. This section explains what you can control and how to control it.

The My Commands dialog box (page 44) allows you to create Text and Graphics commands. These boilerplate commands are relatively easy to create and can save you a lot of time. You can assign a command like “My Address” to a larger block of text, complete with line breaks and formatting.

The improving accuracy section (page 50) includes instructions for the Train Words, Acoustic Settings and Acoustic and Language Model Optimizer dialog boxes.

Here are some resources that have to do with using NatSpeak utilities with Utter Command:

In the Utter Command manual we touch on how Utter Command dovetails with NatSpeak Correction, Vocabulary, Recognition and Train Words utilities in UC Lesson 1 (1.3, 1.4, 1.5, 1.11). Also see the “Dragon NaturallySpeaking” section on UC Exchange.

Tip: Taking the named Touch commands to the next level


Once you get used to naming a mouse click, you might want a little more. Take a look at UC Lesson 10.24 and you’ll find you can combine named mouse touches with other keys in a couple of useful ways.

Here’s a good use of combining a named mouse touch with a letter key. When you’re in an e-mail message in Thunderbird*, you can click on the Sender’s address to drop down a menu that includes Copy e-mail Address and Add to Address Book.

To enable copying the sender e-mail address or adding it to the address book in a single speech step, name a mouse Touch to click on the sender address:

1. Position the mouse on the Sender’s address using a command like “20 By 11”

2. say “Add Touch” to bring up the Touch dialog box

3. name the touch something like “Sender”

4. say “Enter” to put the touch on your Touch list

5. say “Window Close · Yes” to close the UC List dialog box and save changes

6. If necessary, say “Restart NatSpeak” to restart the speech engine.

Now try the command and some combinations.

With an open email in Thunderbird you can say “Sender Touch” and it will click the Sender address to drop down the menu.

Better yet, you can say “Sender Touch c” (or “Sender Touch Charlie”) to copy the address to your clipboard, or “Sender Touch b” (or “Sender Touch Bravo”) to bring up the New Card dialog box with the address entered into it.

Have you found a good application for advanced Touch commands? Tell me about them – reply here or let me know at info@ this website address.

*Thunderbird is a free, open-source, full-featured e-mail program from Mozilla. It’s included in the UsefulFreeSoftware list on the UC Exchange Wiki (say “UC Exchange”).

Tip: Use TinyURLs to tame long Web addresses

Long URLs are awkward in many situations, most especially on Twitter, where character count is paramount. The Firefox Tiny URL Creator add-on gives you more room by reducing any URL to just a few characters.

Tiny URL creator also solves an occasional issue with the Utter Command Site List. The Site List — the list of websites you can get to using a single speech command — handles URLs of up to 100 characters. The Tiny URL Creator eliminates this limitation.

To set up the Tiny URL Creator, download it. It will add a menu item to the Firefox Tools menu. To create a URL from the current URL in Firefox say “Under t t c” to click Tools/Tiny URLCreator/From Current URL. Creating a tiny URL puts it in your system clipboard. Say “This Paste” to paste it anywhere.

See the UC Exchange page UCandFirefox  for more details.

Have you found Firefox or Thunderbird add-ons that make things easier when you’re using speech? Tell me about them – reply here or let me know at info@ this website address.

Tip: Undo for closing a webpage


Ever close a webpage, then wish you hadn’t? In Firefox there’s a shortcut that undoes a tab close: “Shift Control t”.

Ever close several webpages in a row and wish you hadn’t? You can use the same shortcut to get back the last few pages you closed at once, e.g. “Shift Control t Times 3”. Here are some related commands: use “Document Close Times 3” to close tabs and “Control t Times 3” to open blank tabs.

Speak quietly and you don’t need a big stick


Computers can be frustrating when they don’t act as you anticipate. You can anticipate better, however, if you know what they’re going through.

One thing I’ve found with speech recognition is when something is misrecognized the common instinct is to speak more loudly into the microphone — like you’re talking to a person who didn’t quite hear.

This usually makes things worse. Most good microphones are fairly sensitive, and are more likely to interpret the sounds coming out of your mouth more accurately if you speak a little softer rather than louder.

If you notice recognition falling off a bit, speak a little more softly. Picture someone onstage singing so loudly into the microphone that its distorted, and how nice it is when the person backs off a bit. Also think about putting the microphone further away from your mouth — I keep mine about 2 inches away.

Another common cause of recognition falling off is breathing into the microphone. It’s important that the face of the microphone is pointed slightly downward so you’re not breathing directly into it. Picture someone on an outside stage trying to use a microphone in a heavy wind. It’s lots easier to hear when the wind dies down.

Speak quietly and you don't need a big stick


Computers can be frustrating when they don’t act as you anticipate. You can anticipate better, however, if you know what they’re going through.

One thing I’ve found with speech recognition is when something is misrecognized the common instinct is to speak more loudly into the microphone — like you’re talking to a person who didn’t quite hear.

This usually makes things worse. Most good microphones are fairly sensitive, and are more likely to interpret the sounds coming out of your mouth more accurately if you speak a little softer rather than louder.

If you notice recognition falling off a bit, speak a little more softly. Picture someone onstage singing so loudly into the microphone that its distorted, and how nice it is when the person backs off a bit. Also think about putting the microphone further away from your mouth — I keep mine about 2 inches away.

Another common cause of recognition falling off is breathing into the microphone. It’s important that the face of the microphone is pointed slightly downward so you’re not breathing directly into it. Picture someone on an outside stage trying to use a microphone in a heavy wind. It’s lots easier to hear when the wind dies down.

Speech recognition and Eastern equine encephalitis


I have a bone to pick with Nuance. I’ve several times seen Dragon NaturallySpeaking demonstrators wow people by saying a long phrase. “Eastern equine encephalitis” is a favorite. The implication is if computer speech recognition can get this difficult phrase right, it can get anything right.

The reality is just the opposite, and the demonstration gives people an incorrect mental map of how the speech engine works.

It’s important to have a good mental map of how something works. If your mental map is correct your instincts will be correct. If you’re working with a child you probably have an idea of the types of simple mistakes that child is going to make, and you’ll expect and have more patience for simple mistakes than when you’re working with an expert.

The NaturallySpeaking speech engine is different than either working with a child or an expert — it’s very good at some things, but not so good at others. The mix is different than it is with people. NaturallySpeaking is very good at identifying long words and even better at identifying common phrases — Eastern equine encephalitis is both and therefore very easy. It will rarely get this wrong. What’s more difficult for the engine is getting short utterances and uncommon phrases correct. If you give the speech engine more information to work with — a longer word, a phrase, or even the same word drawn out a bit, it has more information to work with and therefore does better.

A more impressive demo phrase for a speech engine would be “at up be”.

With the correct mental map of what’s easy and what’s difficult for the speech-recognition engine, you’ll instinctively speak in phrases and draw things out a bit if you see the engine start to make mistakes. This is probably different from how you tend to adjust to a person who isn’t hearing. In the case of a person a common instinct is to say one word at a time: “Eastern… equine… encephalitis”, which is more difficult for a speech engine.

The good news is a mental map works on instinct — if your mental map is correct, you often don’t even have to think about adjustments, they flow naturally. The bad news is a mental map works on instinct — if it’s incorrect your adjustments won’t work but it will feel like they should be working.

Rulers right

I’ve changed the way I position the mouse rulers, and it’s changed my behavior.

I used to leave Rulers in the default position of top and left. But lately I’ve been using them on the right and bottom, and and I’m liking this better for a couple reasons. I tend to notice them less when they’re tucked above the Taskbar and off to the right. So I tend to leave them on whether I’m using them or not. More important, they don’t change the position of windows, and so don’t affect named mouse touches.

(To change Rulers so they’re just on the right and bottom say “Rulers On”, “Rulers Right Bottom”)

Where do you like Rulers? Let me know here or e-mail at info at this Web address.

Check out NatSpeak Preferred to Pro upgrade

If you’re thinking about upgrading from Dragon NaturallySpeaking Standard or Preferred to Professional now’s the time to do it (Utter Command runs on the NaturallySpeaking Professional engine).

There’s a Dragon NaturallySpeaking pricing special in conjunction with the 10.1 upgrade — for $300 you can upgrade to NaturallySpeaking Professional 10.1 (retail $899) from  the much less expensive Standard or Preferred versions of Dragon 7-9. Dragon resellers are offering the special — here’s a link to one of them: http://www.1st-dragon.com/drupsa.html.

The special pricing is scheduled to last until June 30.