« FJ Cruiser Car Computer Project | Main | Hiring Salespeople comments »

April 27, 2006

Good Speech - Bad Speech

In January I said that Speech Recognition was in the trough of disillusionment.  I predict that by mid next year though, we'll be viewing the technology very differently.  Moore's Law and clever programming are advancing the science of speech recognition very quickly I believe.  People are going to be surprised at how fast this technology is going to improve.

However - no amount of technology will make up for bad application design.  I saw what may be the ugliest prompt ever a few weeks ago.  "Press or say eleven . . ."  I assume there were ten other choices before this prompt and I'm not positive that this was the last prompt.

Please people - I know it is fun to create these applications, but take some time to think about the poor user.  They don't want more choices, they just want to get the information they need and then get off of the phone as quickly as possible.  And for goodness sake, give them the option to speak to a person if they can't figure out how to get what they need from your application.  They're going to find a way out eventually and there is no point in making them mad as they try to figure out the secret back door.

I've been on this soapbox before, but I'm not putting it away until the customer is treated like the important person they are instead of like some rat to be herded through a maze.

April 27, 2006 in Speech Recognition | Permalink


TrackBack URL for this entry:

Listed below are links to weblogs that reference Good Speech - Bad Speech:


Well said Terry.

I would like to point out that some of this is not completely the developer's fault.

In some organizations the design of speech apps is left to business analysts who don't truly understand the medium.

If you are the developer and this is the case for you then you have to fight back. Educate the BAs. We have to quit fostering this garbage on the callers or wide spread acceptance of speech/VIR systems won't happen.

Posted by: Marshall Harrison | Apr 27, 2006 5:14:19 AM

Hi Terry,

I had the opportunity to talk to some of the folks involved with speech recognition for Vista. I truly believe we'll all be pleasantly surprised at the beginning of next year. I got the impression they are working very, very hard to make SR useful for everyone, with little learning curve.

There are some neat tools in development to make it simple and fast for a novice user to get going with speech.


Posted by: Bill Burke | Apr 27, 2006 11:39:10 AM

That's great to hear Bill.

The tools have sure come a long way and speech reco has improved greatly.

The problem lies in that people who design speech applications haven't shifted their paradigm to the new medium. What works on the desktop or web won't work well in speech and we need to shift our thinking accordingly.

As developers we must make the change and then FIGHT for what we know is right.

Posted by: Marshall Harrison | Apr 27, 2006 12:13:33 PM

Hi Marshall,
Referencing your post, above..
"What works on the desktop or web won't work well in speech"

From a speech recognition to the user standpoint, that's going to change, as well - If I'm interpreting where you are coming from correctly. Much of the problem with successful use lies in inadequate hardware, and there's some change in the wind that will cure that, too.


Posted by: Bill Burke | May 9, 2006 3:48:12 PM

Hi Bill,

I wasn't referring to any technical problems but rather to the fact that a VUI needs to be designed seperately rather than voice enabling a web or windows app.

For example a listbox with 15 items won't convert to a VUI design cleanly. While 15 items is OK for a graphical interface you have to approach it differently for voice - a 15 item menu just isn't good design and that is the kind of thing that uninformed BAs tend to do.

Posted by: Marshall Harrison | May 17, 2006 6:10:31 PM