Welcome to SIDEKIT 1.3.1 documentation!

SIDEKIT is an open source package for Speaker and Language recognition.
The aim of SIDEKIT is to provide an educational and efficient toolkit for speaker/language recognition
including the whole chain of treatment that goes from the audio data to the analysis of the system performance.
Authors:Anthony Larcher & Kong Aik Lee & Sylvain Meignier
Version:1.3.1 of 2019/01/22

See also

News for SIDEKIT 1.3.1:

  • new sidekit_mpi module that allows parallel computing on several nodes (cluster) MPI implementations are provided for GMM EM algorithm, TotalVariability matrix EM estimation and i-vector extraction see MPI for more information about MPI
  • new FactorAnalyser class that simplifies the interface
    Note that FA estimation and i-vector extraction is still available in StatServer but deprecated
  • i-vector scoring with scaling factor
  • uncertainty propagation is available in PLDA scoring

What’s here?


When using SIDEKIT for research, please cite:

Anthony Larcher, Kong Aik Lee and Sylvain Meignier,
An extensible speaker identification SIDEKIT in Python,
in International Conference on Audio Speech and Signal Processing (ICASSP), 2016


This documentation is available in PDF format here

Contacts and info



Indices and tables