如何才能执行,而不是麦克风上的讲话从一个音频文件(.MP3,WAV)未来语音识别?
How can I perform speech recognition on speech coming from an audio file (.mp3, wav) instead of the microphone ?
我希望能够做到这一点从C#.NET和Delphi。
I want to be able to do that from C#.NET and Delphi.
本文具体回答你的问题:
使用WAV文件输入与SR引擎 http://msdn.microsoft.com/en-us /library/ms717071(VS.85).aspx
Using WAV File Input with SR Engines http://msdn.microsoft.com/en-us/library/ms717071(VS.85).aspx
请参阅基本信息如下文章:
See the following articles for general info:
http://msdn.microsoft.com/en-us/magazine/ cc163663.aspx
http://en.wikipedia.org/wiki/Speech_Application_Programming_Interface
http://msdn.microsoft.com/ EN-US /库/ ms723627(VS.85)的.aspx