Description: 基于Microsoft Speech SDK在VC++6.0环境下编写的text to speech的程序-Based on the Microsoft Speech SDK in VC++ 6.0 environment prepared text to speech of the procedures Platform: |
Size: 2305024 |
Author:梁丁宏 |
Hits:
Description: VC6.0编译可运行的字典语音识别,加载了xml文档,只能识别英语。微软语音识别分两种模式:文本识别模式和命令识别模式.此两种模式的主要区别,主要在于识别过程中使用的匹配字典不同.前者使用的是通用字典,特点是内容多,覆盖的词汇量大,字典由sdk提供.适用于没有预定目标的随机听写之类的应用.同时因为词汇量大直接导致识别的精度降低,识别速度较慢.后者的字典需要 开发者自己编写,就是所说的xml文件.-VC6.0 compiler can run dictionary speech recognition, loading the XML document. Microsoft speech recognition points two modes: text recognition mode and command recognition mode. The main difference between the two different modes mainly depends on the identification process, use matching dictionary. The former is using different general dictionary, characteristic is more content, cover vocabulary is big, dictionary. Suitable for by the SDK provides no reservation target the application of random dictation. Also because such vocabulary big directly to the identification precision of lower, recognition at a slower speed. The latter dictionary needs, it is says developer himself write the XML file.
Platform: |
Size: 2075648 |
Author:mr chen |
Hits: