How to train the SAPI recognizerhttp://blogs.msdn.com/b/tsfaware/archive/2010/03/15/how-to-train-the-sapi-recognizer.aspxImplementing SAPI training is relatively hard, and the documentation doesn’t really tell you what you need to know. ISpRecognizer2::SetTrainingState switches the recognizer into or out of training mode. When you go into training mode, all that reallyen-USTelligent Evolution Platform Developer Build (Build: 5.6.50428.7875)re: How to train the SAPI recognizerhttp://blogs.msdn.com/b/tsfaware/archive/2010/03/15/how-to-train-the-sapi-recognizer.aspx#9994457Mon, 12 Apr 2010 16:23:02 GMT91d46819-8472-40ad-a661-2c78acb4018c:9994457Eric C Brown<p>Most of the adaptation actually occurs when the recognizer moves out of training state.</p> <p>This is engine dependent; other SAPI-compatible engines could adapt at recognition time.</p> <div style="clear:both;"></div><img src="http://blogs.msdn.com/aggbug.aspx?PostID=9994457" width="1" height="1">re: How to train the SAPI recognizerhttp://blogs.msdn.com/b/tsfaware/archive/2010/03/15/how-to-train-the-sapi-recognizer.aspx#9992347Thu, 08 Apr 2010 11:25:50 GMT91d46819-8472-40ad-a661-2c78acb4018c:9992347John<p>This is great thanks. &nbsp;When does the engine actually adapt to the audio and text you give it?</p> <p>thank you!</p><div style="clear:both;"></div><img src="http://blogs.msdn.com/aggbug.aspx?PostID=9992347" width="1" height="1">re: How to train the SAPI recognizerhttp://blogs.msdn.com/b/tsfaware/archive/2010/03/15/how-to-train-the-sapi-recognizer.aspx#9984444Wed, 24 Mar 2010 16:19:35 GMT91d46819-8472-40ad-a661-2c78acb4018c:9984444Eric C Brown<p>Training is a two-part process. &nbsp;The recognizer actually has to see the audio twice; you can't just build a set of transcripts and toggle training mode on and off.</p> <div style="clear:both;"></div><img src="http://blogs.msdn.com/aggbug.aspx?PostID=9984444" width="1" height="1">re: How to train the SAPI recognizerhttp://blogs.msdn.com/b/tsfaware/archive/2010/03/15/how-to-train-the-sapi-recognizer.aspx#9983997Wed, 24 Mar 2010 00:32:05 GMT91d46819-8472-40ad-a661-2c78acb4018c:9983997Naveen<p>Do you have to do it piecewise ? </p> <p>Why do you have to get the audio and text using &nbsp;ISpRecoResult::GetAudio and not a prerecorded wav file and its corresonding text ? </p> <p>Thanks</p><div style="clear:both;"></div><img src="http://blogs.msdn.com/aggbug.aspx?PostID=9983997" width="1" height="1">