Skip to content
/ ssp Public

Speech Signal Processing - a small collection of routines in Python to do signal processing

License

Notifications You must be signed in to change notification settings

idiap/ssp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

3949632 · Aug 7, 2018
Aug 7, 2018
Nov 20, 2015
Jun 25, 2013
Mar 12, 2016
Jun 25, 2013
Jun 25, 2013
Aug 7, 2018
Aug 7, 2018
Aug 7, 2018
Aug 7, 2018
Oct 24, 2013
Aug 7, 2018
Apr 4, 2015
Aug 7, 2018

Repository files navigation

SSP - Speech Signal Processing module

Overview

SSP is a package for doing signal processing in python; the functionality is biassed towards speech signals. Top level programs include a feature extracter for speech recognition, and a vocoder for both coding and speech synthesis. The vocoder is based on linear prediction, but with several experimental excitation models. A continuous pitch extraction algorithm is also provided, built around standard components and a Kalman filter.

There is a "sister" package, libssp, that includes translations of some algorithms in C++. Libssp is built around libube that makes this translation easier.

SSP is released under a BSD licence. See the file COPYING for details.

Installation

To install SSP from git, just clone it into a working directory:

cd ~/src  # Just for example
git clone [email protected]:idiap/ssp.git
cd ssp

Or, if you work in a different directory:

cd where-I-work
ln -s ~/src/ssp/pitch.py
ln -s ~/src/ssp/codec.py

i.e., you shouldn't need to set PYTHONPATH

Then you can say

pitch.py test.wav  # Graphical view of what's going on
codec.py -h
codec.py -r 22050 -p EM1.wav EM1.lf0

If you know what buildout is:

python bootstrap.py
./bin/buildout

Alternatively, SSP is available on PyPI at https://pypi.python.org/pypi/ssp That's available by typing

pip install ssp  # Root level installation

or

pip install ssp --user  # User level in ~/.local

Note that the PyPI package is very likely to be out of date!

Otherwise, see the wiki at https://github.com/idiap/ssp/wiki

Publications

The pitch tracker in SSP is documented in the paper:

@Article{Garner2013,
  author =       "Garner, Philip N. and Cernak, Milos and Motlicek,
                  Petr",
  title =        "A Simple Continuous Pitch Estimation Algorithm",
  journal =      "IEEE Signal Processing Letters",
  year =         2013,
  month =        "January",
  volume =       20,
  number =       1,
  pages =        "102--105",
  doi =          "10.1109/LSP.2012.2231675"
}

and there is a downloadable pdf.

The codec is documented in a technical report:

@TechReport{GarnerTech2015,
  author =      "Garner, Philip N. and Cernak, Milos and Potard, Blaise",
  title =       "A simple continuous excitation model for parametric vocoding",
  institution = "Idiap Research Institute",
  year =        2015,
  type =        "Idiap-RR",
  number =	    "03-2015",
  month =       "January"
}

and again there is a downloadable pdf.

-- Phil Garner June 2013

About

Speech Signal Processing - a small collection of routines in Python to do signal processing

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages