创建语音库总结

ROS中PocketSphinx语音识别_安装arbotix simulator仿真环境_turtlebot的仿真语音控制这个博客也有写到可参考：http://www.pirobot.org/blog/0022/http://blog.csdn.net/zouxy09/article/details/7949126Creatin

光子乘羽

2330人浏览 · 2016-12-20 15:06:48

光子乘羽 · 2016-12-20 15:06:48 发布

ROS中PocketSphinx语音识别_安装arbotix simulator仿真环境_turtlebot的仿真语音控制

这个博客也有写到

可参考：http://www.pirobot.org/blog/0022/

http://blog.csdn.net/zouxy09/article/details/7949126

Creating A Vocabulary

It is easy to create a new vocabulary or corpusas it is referred to in PocketSphinx. First, create asimple text file with one word or phrase per line. Here is acorpus that could be used to drive your robot around using voicecommands. We will store it in a file called nav_commands.txt in the config subdirectory of the pi_speech_tutorial package:

$ roscd pi_speech_tutorial/config
$ more nav_commands.txt

You should see the following list of phrases:

pause speech
continue speech
move forward
move backward
move back
move left
move right
go forward
go backward
go back
go left
go right
go straight
come forward
come backward
come left
come right
turn left
turn right
rotate left
rotate right
faster
speed up
slower
slow down
quarter speed
half speed
full speed
stop
stop now
halt
abort
kill
panic
help
help me
freeze
turn off
shut down
cancel

Feel free to add, delete or change some of these words or phrases before proceeding to the next step.

When you enter your phrases, try not to mix upper and lower case and donot use punctuation marks. Also, if want to include a number suchas 54, spell it out as "fifty four".

Before we can use this corpus with PocketSphinx, we need to compileit into special dictionary and pronunciation files. Thiscan be done using the online CMU language model (lm) tool located at:

http://www.speech.cs.cmu.edu/tools/lmtool-new.html

Follow the directions to upload your nav_commands.txtfile, click the "Compile Knowledge Base" button, then download theresulting compressed tarball that contains all the language modelfiles. Extract thesefiles into the config subdirectory of the pi_speech_tutorial package. The files will all begin with the same number, such as 3026.dic, 3026.lm,etc. These files define your vocabulary as a language model thatPocketSphinx can understand. You can rename all these files tosomething more memorable using a command like the following (the4-digit number will likely be different in your case):

$ roscd pi_speech_tutorial/config
$ rename -f 's/3026/nav_commands/' *

Next, take a look at the voice_nav_commands.launch file found in the launch subdirectory of the pi_speech_tutorial package. It looks like this:

As you can see, we launch the recognizer.py node in the pocketsphinx package and we point the lm and dict parameters to the files nav_commands.lm and nav_commands.dic created in the steps above. Note also that the parameter output="screen" is what allows us to see the real-time recognition results in the launch window.

Launch this file and test speech recognition by monitoring the /recognizer/output topic:

$ roslaunch pi_speech_tutorial voice_nav_commands.launch

And in a separate terminal:

$ rostopic echo /recognizer/output

Try saying a few navigation phrases such as "move forward", "slow down"and "stop". You should see your commands echoed on the /recognizer/output topic.

利用在线工具建立语言模型

（1）创建一个语料库：

语料库实际上就是一些文本的集合，包含了你需要识别的语音的文字的一些集合，例如句子啊，词啊等等。

#vi corpus.txt

输入如下内容：

stop

forward

backward

turn right

turn left

保存退出

（2）利用在线工具LMTool建立语言模型：