saurabh-kataria / pysepm

Python implementation of performance metrics in Loizou's Speech Enhancement book

pysepm - Speech Enhancement Performance Measures (Quality and Intelligibility) Implemented in Python

Python implementation of objective quality and intelligibilty measures mentioned in Philipos C. Loizou's great Speech Enhancement Book. The Python implementations are checked with the MATLAB implementations attached to the book (see Link)

Requirements

gcc compiler
cython
numpy
scipy
pystoi
pypesq 

Implemented Speech Quality Measures

• Segmental Signal-to-Noise Ratio (SNRseg)
• Frequency-weighted Segmental SNR (fwSNRseg)
• Log-likelihood Ratio (llr)
• Weighted Spectral Slope (wss)
• Perceptual Evaluation of Speech Quality (pesq)
• Composite Objective Speech Quality (composite)

Implemented Speech Intelligibility Measures

• Short-time objective intelligibility (stoi)

Install with pip

The setup.py is not finished yet. You have to install the dependencies by hand.

First install Cython (Required for python-pesq):

pip3 install Cython

Then install python-pesq and pystoi:

pip3 install https://github.com/schmiph2/python-pesq/archive/master.zip
pip3 install https://github.com/schmiph2/pystoi/archive/master.zip

Finally install pysepm:

pip3 install https://github.com/schmiph2/pysepm/archive/master.zip