Talkbox, a set of python modules for speech/signal processing
Talkbox, to make your numpy environment speech aware !
Talkbox is set of python modules for speech/signal processing. The goal of this
toolbox is to be a sandbox for features which may end up in scipy at some
point. The following features are planned before a 1.0 release:
* Spectrum estimation related functions: both parametic (lpc, high
resolution methods like music and co), and non-parametric (Welch,
* Fourier-like transforms (DCT, DST, MDCT, etc...)
* Basic signal processing tasks such as resampling
* Speech related functionalities: mfcc, mel spectrum, etc..
* More as it comes
I want talkbox to be useful for both research and educational purpose. As such,
a requirement is to have a pure python implementation for everything - for
educational purpose and reproducibility - and optional C for speed.
You can download the latest distribution from PyPI here: http://pypi.python.org/pypi/scikits.talkbox
You can install scikits.talkbox for yourself from the terminal by running:
pip install --user scikits.talkbox
If you want to install it for all users on your machine, do:
pip install scikits.talkbox
On Linux, do sudo pip install scikits.talkbox
If you don't yet have the pip tool, you can get it following
This package was discovered in PyPI.