ROS machine voice

Speech recognition function package ：pocketsphinx
  because pocketsphinx Only to Ubuntu14.04,ROS Kinetic I won't support it sudo apt-get install ros-kinetic-pocketsphinx, So in kinetic The installation is a little troublesome .
 
Switch to a bash：

exec bash 

Switch to a zsh：

exec zsh

1, Installation dependency ros-kinetic-audio-common

sudo apt-get install ros-kinetic-audio-common

2, Installation dependency libasound2

sudo apt-get install libasound2

3, Installation dependency libgstreamer0.10

zsh Unable to run , however bash Sure , Here we are going to bash Add to zsh in

sudo apt-get install gstreamer0.10-*

4, Installation dependency python-gst0.10

sudo apt-get install python-gst0.10

5, Install Feature Pack libsphinxbase1_0.8-6

Download link ：https://packages.debian.org/jessie/libpocketsphinx1

sudo dpkg -i libpocketsphinx1_0.8-5_amd64.deb

6, Install Feature Pack libpocketsphinx1_0.8-5

Download link ：https://packages.debian.org/jessie/libpocketsphinx1

sudo dpkg -i libpocketsphinx1_0.8-5_amd64.deb

7, Install Feature Pack gstreamer0.10-pocketsphinx

Download link ：https://packages.debian.org/jessie/gstreamer0.10-pocketsphinx

sudo dpkg -i gstreamer0.10-pocketsphinx_0.8-5_amd64.deb

8, Enter the workspace Directory , download pocketsphinx The source code of the function package and compile

cd ~/catkin_ws/src
git clone https://github.com/mikeferguson/pocketsphinx
cd ~/catkin_ws/
catkin_make
source devel/setup.bash

9, Download and install the English voice pack pocketsphinx-hmm-en-tidigits_0.8-5

Download link ：https://packages.debian.org/jessie/pocketsphinx-hmm-en-tidigits

sudo dpkg -i pocketsphinx-hmm-en-tidigits_0.8-5_all.deb

10, stay pocketsphinx Create a model Catalog , Store the unzipped voice model file

cd ~/catkin_ws/src/pocketsphinx
mkdir model
sudo cp /usr/share/pocketsphinx/model/* ~/catkin_ws/src/pocketsphinx/model -r

11, modify recognizer.py file cd ~/catkin_ws/src/pocketsphinx/nodes

（1） Comment out self.asr.set_property(‘configured’, True)
（2） add to lm,dict,hmm Support English recognition （ If it is another language, you can change to another path ）

self.asr.set_property('lm', '/usr/share/pocketsphinx/model/lm/en/tidigits.DMP')
self.asr.set_property('dict', '/usr/share/pocketsphinx/model/lm/en/tidigits.dic')
self.asr.set_property('hmm', '/usr/share/pocketsphinx/model/hmm/en/tidigits')