[Dragon on the cheap is a series of articles about how to achieve just about the highest level of voice recognition, using high-quality, low-cost equipment and approaches. This article features a $9 USB sound adapter from, no surprise, eBay.]

[Dragon on the cheap is a series of articles about how to achieve just about the highest level of voice recognition, using high-quality, low-cost equipment and approaches. This article tackles how to acquire an effective, powerful, high and computer for not much money.]

Here's something I've written to help people struggling with hands-free computing. I just updated it today to included an admittedly convoluted solution (read the entire message) that enables me to use a Macintosh hands-free. Good luck!

***** begin *****

Adaptive technologies for Windows users (updated 9/9/2005)

I have been doing hands-free computing and programming for three years now, using an entirely different approach to hands-free cursor movement and mouse button clicking. The solution is to use the best technology for the job, and let's face it--voice-recognition technology is very bad at moving the cursor and clicking mouse buttons.

Greetings from Research Lab Inc. We are pleased to inform you that we have recently released Embedded Speech Recognition using LVCSR based on ISIP research, Embedded Speaker Verification, Embedded Speech Synthesis based on Festival Research. Detailed documentation is mentioned here.

http://www.research-lab.com/embedded.htm

Evaluation Windows CE downloads are available on the mentioned link

Submitted by Joeblake1 on Tue, 08/30/2005 - 01:23.

Here's how I've "remotely trained" my DNS to a speaker who doesn't even know they're doing it (ie training the Dragon).

Firstly, some more caveats: or the same ones in different words. I mentioned that it could be "fiddly" because it depends on which version of DNS you're using. Whilst I have V6 and V7, and the V7 upgrade, I reverted back to V5 because it was faster and easier. Secondly, there are three parts, the first part, creation the training document is reasonably straight forward, the second part is probably the most difficult, the third is easy, but initially time consuming.

The internal search function has been disabled and replaced by a Google Custom Search.

If you look on the upper right corner of each page you will see the input area and the Search button.

There's nothing like being completely confused when you visit a website and are just looking for help! Let me show you areas where you can research or ask for help on here.

• To find the messaging areas go to the forums or read users blogs
• If you are looking for frequently asked questions, go to the faq listed under the help section. If you don't find your answer there, it's suggested that you search the site for keywords or ask your question in the forums.

Clicking on 'recent posts' in the menu will give you a page that showing the type of post, subject of the post, the author of the post, how many replies have been made to the post and the time elapsed since the last response. These are in newest first order. Many subscribers refer to the 'recent posts' entry as "the tracker". You may bookmark the 'recent posts' page and return there for easy reading.

Speech Computing's built-in form-based content editing approach is fine for many applications, but if you have a lot of text to create, or you wish to convert existing content, or if you are using a s

For the purpose of this article, comments and replies are considered the same.

Comments allow users to interact with messages on Speech Computing, to respond to an article, offer their own ideas, make additions, or supply a critique.

Leaving comments

When you bring up an article to read, look for comment-related links at the bottom of the article. If you're not logged in, this might read "login or register to post comments".