Tuesday, January 10, 2012

[Reminder] You don't need a Kinect to do Speech Recognition on Windows

Robert Lucero's Testing Blog - Speech 101, Part 2 - Using C# to Recognize “Hello World”

In my last post I covered how to perform basic speech recognition with a simple grammar and a “Hello World” WAV recording in C++. This post will cover how to accomplish what was in the previous post, but this time using the managed APIs.

Sound Check, Round 2

The support files for this example can be found here. Both HelloWorld.xml and HelloWorld.wav are required.

Again, in addition to the helper files the Windows SDK is also required.

Hello, Hello? Is this C#?

The most basic Speech recognition work flow is this:

  1. Create a Speech Recognition Engine
  2. Load a Grammar
  3. Set the Engine’s input
  4. Handle Recognition Events
  5. Start Recognition

First, launch Visual Studio and create a new Visual C# Console Application. Copy the two helper files to the project root directory, add them to the project and set their properties to “Copy on Build”.



MSDN’s Documentation on the Speech Recognition Engine:

MSDN’s Starting Point for Speech Recognition:


I know you all know this but... Seems one of the things allot people are doing with the Kinect for Windows SDK is voice/speech recognition. You know you don't need a Kinect to do that, right? Windows has has speech functionality built in since Vista (and you could add it to XP). You can start adding speech recognition to your apps today, no Kinect required...

No comments: