simpleblog RSS feed http://blog.8pixel.net/ An RSS feed for Simpleblog EN <![CDATA[Esto es pata ti hackxcrack]]>
PoR AqUi PaSo WiLhAcK
]]> 10/2/2009 http://blog.8pixel.net/?view=plink&id=118 118 <![CDATA[Barriers to Adopting Speech Recognition]]>
Welcome to the CoolSoft Blog.  Let me introduce myself.  My name is Paul Lagassey, and I am the founder and manager of CoolSoft, LLC.  I live in Vero Beach, Florida and I'm an entrepreneur.  I've been reading a lot about Blogs and a number of people have suggested that I start one for CoolSoft.  After doing some research, it seems like a good idea.

To get my feet wet, I started a Blog on my personal website. I thought it would take a little time to get my feet wet, but after my first posting I feel like I've got the hang of it.

Before going on, I have to take a step back and give a few people credit.  Before starting, I did some research and found several blog applications that were compatible with our .asp based website.  My developers at MontrealSoft choose Simple Blog 3.0, which turns out to be a great choice.  In keeping with its name, its simple and easy to use, and has all the basic features one really needs.  So, I have to give credit to http://www.8pixel.net/?pageID=420.  The developer, from Reykjavik, Iceland, has been working on websites and web programming for the past 5 years or so, and is currently studying computer science at Reykjavík University.  And of course, I have to give credit to Eric Monet at MontrealSoft for making this selection out of four possible choices.  Now on to my topic:

Since several of my ventures are in the field of speech recognition (also known in the industry as voice recognition), and because CoolSoft's flagship products are speech recognition software, I decided this would be a good first topic.

Through my seven years of experience in the field of speech recognition, I’ve learned that there are three main barriers that keep many computer users away from adopting this great and exciting technology.  These are the time it takes to setup the system, the learning curve, and the need to modify work habits.  If you too have one or more of these issues with speech recognition, then maybe you’ll find my thoughts on the subject useful.  Then I hope you'll try one of our titles.  So here we go:

I’ve found that many trial users who download a speech recognition program don’t want to invest the time to setup and train the speech recognition engine and configure the microphone.  It seems like a daunting task.  From some of the support requests we get, it becomes obvious that many trial users don’t even bother to read the instructions, and consequently don't know about training the speech engine.  Some people just skip the step without realizing that without training they won't get good results from the program.  And some users don’t bother with getting a good quality headset microphone - why spend the money?  A decent microphone only costs about $20.00.  When a user skips training, or uses a poor quality microphone or a desktop or built-in microphone, the recognition accuracy results are usually poor and the user dismisses the product as just another of many downloads that doesn't work.  The truth is that training only takes about 20 to 30 minutes, and then its done for good.  This is a small investment of considering the long-term rewards.   When the speech engine is trained properly (at least two or three training sessions), a good quality headset microphone is used (a headset microphone insures consistent positioning of the microphone), and if the microphone is configured before each use; the accuracy of speech recognition is typically 95% or better.  Isn’t this a worthwhile investment to enhance your computing experience for a lifetime?

Learning how to use the program and learning the speech commands is another impediment.  To many users, this also appears as a daunting task, but the truth is that its easy - especially if the developer of the software makes it easy.  A good speech recognition program is built from the ground up with the user in mind, and this means making it easy for the user to succeed with the program.  A good speech recognition program has a user interface designed to be intuitive and developer incorporates both quick reference and detailed documentation that makes it easy for the user to learn the program and speech commands.  The speech programs offered by CoolSoft and SpeechVibe (discussed below) also have demo videos (a picture is worth 1,000 words) that show how to use the programs, “What can I say?” dialogs, tool tips and “say what you see” features.  Our speech recognition programs make it easy for you to overcome this barrier.  Try one and you’ll see.

The third issue is user related.  To use speech recognition effectively, you have to change your habits. When typing, most people correct their mistakes as they go along.  With speech recognition it is more efficient to dictate your text first, and then make your corrections.  We humans are creatures of habit, and many of us (including myself at one time) are resistant to this change of habit.  But once you get the hang of it, you might find that using speech recognition is truly much better than typing.  I was at a speech recognition conference several years ago, and one of the speakers presented some statistics.  He said their research showed that the average person types at 35 words per minute with a 5% error rate.  The average user of speech recognition achieves a rate of 50 words per minute with the same 5% error rate.  This represents a whopping one-third increase in productivity.  I’d like to see any other type of program match that milestone.

In closing, I'll make two more comments about speech recognition accuracy.  First, a speech engine cannot make spelling mistakes.  The recognition errors come from recognizing one word for another (like “pest” instead of “test”).  This is great for people (like me) who aren’t good spellers.  Second, a speech program that has a correction feature and utilizes the user adaptation capabilities of a speech engine will learn when a recognition error is corrected.  Then, the speech engine is unlikely to repeat that mistake again.  SpeechVibe is one such program that makes use of this feature.

For those of you interested in trying speech recognition, I recommend SpeakToText (available at http://www.CoolSoftLLC.com) as a good program to introduce yourself to the world of speech recognition.  It’s a simple, easy to use program that satisfies the needs of most users, providing much of the functionality of high priced speech recognition software at a fraction of the cost.

Once you’re hooked, you’ll want to upgrade to SpeechVibe or SpeechVibe professional.  I’m working on a plan where users of SpeakToText will get a special upgrade price.  SpeechVibe is a really kick-ass speech product that in my opinion gives Dragon Naturally Speaking a good run for its money.  Try it, and you’ll see what I mean.   Now, you may ask yourself why I'm recommending the product of another company.  Simple - Philippe Roy the developer is brilliant, the program is great, I invested money in the company, and by making this recommendation I'd doing a service to our customers - everyone wins.

Personally, I think SpeechVibe far outperforms the Windows Vista native speech recognition (yes, Windows Vista has speech recognition built-in).  The best part is that SpeechVibe works in Windows 2000 and Windows XP – so you don’t have to, umm, upgrade, to Vista to get speech recognition.  For example, one of my friends installed Windows XP on his new Vista machine and called that an upgrade.  You can get SpeechVibe on the CoolSoft website or go directly to http://www.SpeechVibe.com. Checkout the demo videos, download the free trial and give it a spin. 

Looking forward to comments from the audience,



Paul Lagassey
]]> 9/29/2008 http://blog.8pixel.net/?view=plink&id=117 117