Building a voice internet - Part 1

Voice - the most natural, intuitive, and easy to use interface that has been ever invented. 

We have seen CLI (CommandLine Interface) Old timers like me are still very comfortable kicking up a DOS window and doing findstr and dir /s operations....

Then we had its uptown cousin, the GUI (Graphical User Interface) that has really changed the way PCs and web are used by everyone and the point and click model is known worldwide by about 700 million odd internet users.

For many decades now a 3rd interface using Voice, I call it VUI (Voice User Interface) is being proposed. In order to build a VUI, a few fundamental technologies, ASR (Automatic Speech Recognition), TTS (Text To Speech) and IVR (Interactive Voice Response) are needed. Whilst IVR is quite mature now. ASR and TTS have remained in the realm of science fiction till about two decades back.

That is when a breakthrough was made at Carnegie Mellon and speech recognition with high degree of accuracy could be used. This led to the birth of many applications and companies in the 90s that used speech recognition to automate some of these tasks. 
In late 90s I lived through a transition where local search or directory assistance/yellow pages enquiries were first semi-automated (partially machine, partially done by call centre agents) and later everything was automated. 

Today, services like 1-800-GOOG-411 and 1-800-LIVE-411 are completely automated and testimony to the fact that speech recognition can be used in commercial grade applications.  

Next: The coming decade of voice internet.

 del.icio.us  Stumbleupon  Technorati  Digg 

 

What did you think of this article?




Trackbacks
  • No trackbacks exist for this entry.
Comments
  • No comments exist for this entry.
Leave a comment

Submitted comments will be subject to moderation before being displayed.

 Enter the above security code (required)

 Name

 Email (will not be published)

 Website

Your comment is 0 characters limited to 3000 characters.