语音识别系统CMUsphinx环境安装

安装语音识别系统主要是为了在tutrlebot上应用, 所以先安装ROS:

教程: http://www.cnblogs.com/qixianyu/p/6590917.html

          http://www.cnblogs.com/liu-fa/p/5779206.html

接下来安装CMUsphinx：

步骤：

     1. 点击官网下面的链接下载:  https://cmusphinx.github.io/wiki/download/

• Pocketsphinx — recognizer library written in C.
• Sphinxtrain — acoustic model training tools
• Sphinxbase — support library required by Pocketsphinx and Sphinxtrain
• Sphinx4 — adjustable, modifiable recognizer written in Java

     2.  安装 :   https://cmusphinx.github.io/wiki/download/

         在自己打算安装的目录里，解压全部下载的包，确认 sphinxbase-X.x 和 pocketsphinx-X.x 是同一个版本。

         安装依赖项：

                gcc, automake, autoconf, libtool, bison, swig at least version 2.0, python development package, pulseaudio development package

         进入sphinxbase所在文件夹：

                 %cd sphinxbase-5prealpha

                 % ./autogen.sh

                 % ./configure


                 % make

                 %sudo make install

             设置路径：

                  export LD_LIBRARY_PATH=/usr/local/lib

                  export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig

          进入pocketsphinx所在文件夹：

                 % ./autogen.sh

                 % ./configure

                 % make

                 % make install

     3. test安装时否成功

               新终端：

                %pocketsphinx_continuous -inmic yes

               如报错：

                     If you get an error such as:error while loading shared libraries: libpocketsphinx.so.3, you may want to check your linker configuration with LD_LIBRARY_PATH environment variable described above.

               未出错则安装成功。