Skip to main content

Toolchains for speaker recognition and anti-spoofing using PLDA

Project description

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:

Project details

Release history Release notifications

This version
History Node


History Node


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date (105.0 kB) Copy SHA256 hash SHA256 Source None Mar 25, 2015

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page