skip to navigation
skip to content

xspear.fast_plda 1.1.1

Toolchains for speaker recognition and anti-spoofing using PLDA

Toolchain for fast and scalable PLDA

This package contains scripts that run the fast and scalable PLDA [1] and two-stage PLDA [2]. The package uses the framework of Bob `Spear` for handling the protocol, the toolchain and doing the post-processing (whitening and length-normalization).

If you use this package and/or its results, please you must cite the following publications:

[1] The original Fast PLDA paper published at S+SSPR 2014::

author = {Sizov, A and Lee, K.A. and Kinnunen, T.},
title = {Unifying Probabilistic Linear Discriminant Analysis Variants in Biometric Authentication},
booktitle = {Proc. S+SSPR},
year = {2014},
url = {to appear},

[2] Two-stage PLDA applied for anti-spoofing:

title={Joint Speaker Verification and Anti-Spoofing in the i-Vector Space},
author={Sizov, A. and Khoury, E. and Kinnunen, T. and Wu, Z. and Marcel, S.},
journal={Information Forensics and Security, {IEEE} Transactions on},

[3] The Spear paper published at ICASSP 2014::

author = {Khoury, E. and El Shafey, L. and Marcel, S.},
title = {Spear: An open source toolbox for speaker recognition based on {B}ob},
booktitle = {IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2014},
url = {},


Just download this package and decompress it locally::

$ wget
$ unzip
$ cd xspear.fast_plda-1.1.1

Use buildout to bootstrap and have a working environment ready for

$ python
$ ./bin/buildout

This also requires that bob (== 1.2) is installed.

Example of use

To reproduce our spoofing experiments you need to download the data
$ wget
$ unzip

and modify necessary directories for the scripts/TIFS2015/reproduce_* shell scripts.

For more details and options, please use --help option for the executable files in the bin/ directory:

$ bin/ --help

.. _Spear:  
File Type Py Version Uploaded on Size (md5) Source 2015-03-25 102KB