Contents tagged with Longhorn Speech
-
WinFX & Speech Confusion
Just discovered Robert Brown's blog. He writes in this post about how to open prerecorded audio files for recognition, complete with vb sample code for the WinFX B1rc ... however, instantiating the SpeechRecognizer (should be easy) fails with (a COMException):
-
Longhorn Speech API Article
Recently published was my brief article to Developer.Com on the Longhorn Speech API, and how to do some basic recognition and synthesis. Code sample included!
-
Longhorn Component: "Hoolie"
I've been looking into the inner workings of Longhorn 4074, and have discovered there's much more here than meets the eye (or keyboard). I'm sure a lot of this is under wraps because it's not MS' way to put forth something that's not usable yet (see the hidden windows manager command for an example of this -- it's cool, but it's not working for all video cards, slow, etc...but still in development).
-
Announcing.... GetMyNews for Longhorn
I would post a screenshot, but there's not much to see. Rather, this is for your aural pleasure. GetMyNews vA1 listens for any of a set of commands listed in
it'sits (and that's one of my pet peeves) grammar file, NewsCommand.grxml, and will go out and hit an rss feed provided by http://googlenews.74d.com . -
Audio Under Longhorn
One of the questions I get asked most often about Longhorn is in regards to audio hardware. 1) What is a card that works under Longhorn, and 2) How do I get the drivers working?
-
Longhorn Speech - Context Sensitivity
“The language model describes in a statistical fashion the likelihood of specific word sequences occurring at a given time. In other words, what is the probability of the word "America" following the words "United States of"? These statistics are determined by analyzing a large collection of written and spoken text. Because of their statistical nature, they are flexible - any word sequence has some, albeit small, probability of occurring - but lack the rigor required for high recognition accuracy.”