This project is to better understand how to identify a user by their speech and further to understand what they are saying. It will be tackled in two parts:
-
Speaker Identification
-
Speech to Text Recognition
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
The following dependencies are required for this project to work. The commands given below are how to install each one.
$ sudo apt-get install python-pip python-dev --yes
$ pip install --upgrade pip --user
$ pip install --upgrade setuptools --user
$ sudo apt-get install python-numpy python-scipy python-skimage python-matplotlib ipython ipython-notebook python-pandas python-sympy python-nose --yes
$ pip install tensorflow --user
$ pip install seaborn pandas --user
$ pip install jupyter --user
$ pip install tflearn --user
$ pip install librosa --user
$ pip install pydub --user
$ pip install numpy matplotlib scipy sklearn hmmlearn simplejson eyed3 pydub --user
$ sudo apt-get install python-tk --yes
$ git clone https://github.com/tyiannak/pyAudioAnalysis.git
$ wget https://downloads.sourceforge.net/project/audiotools/audiotools/2.16/audiotools.2.16.tar.gz?r=https%3A%2F%2Fsourceforge.net%2Fprojects%2Faudiotools%2Ffiles%2F&ts=1490043434&use_mirror=dronedata
$ mv audiotools.2.16.tar.gz\?r\=https%3A%2F%2Fsourceforge.net%2Fprojects%2Faudiotools%2Ffiles%2F audiotools.2.16.tar.gz
$ tar -xzvf audiotools.2.16.tar.gz
$ sudo apt-get install libcdio-dev libcdio-paranoia-dev
$ cd audiotools-2.16/
$ sudo make install
Test Installation with:
$ audiotools-config