`Voxforge`_ offers a collection transcribed speech for use with **Free** and **Open Source Speech Recognition Engines**.
In this package, we design a speaker recognition protocol that uses a **small subset of the english audio files** (only 6561 files) belonging to **30 speakers** randomly selected.
This subset is split into three equivalent parts: Training (10 speakers), Development (10 speakers) and Test (10 speakers) sets.
This package serves as a toy example of speaker recognition database while testing `xbob.spkrec`_.
The `xbob.spkrec`_ is developed at Idiap during its participation to the `NIST SRE 2012 evaluation`_. If you use this package and/or its results, please cite the following
publications:
1. The original paper presented at the NIST SRE 2012 workshop::
@inproceedings{Khoury_NISTSRE_2012,
author = {Khoury, Elie and El Shafey, Laurent and Marcel, S{\'{e}}bastien},
month = {dec},
title = {The Idiap Speaker Recognition Evaluation System at NIST SRE 2012},
The data can be downloaded from its original URL (on Voxforge) and extracted by running `download_and_untar.sh`_ that takes as input the path in which the data will be stored::
parser.add_argument('-d','--directory',default='',help="if given, this path will be prepended to every entry returned.")
parser.add_argument('-e','--extension',default='',help="if given, this extension will be appended to every entry returned.")
parser.add_argument('-u','--purpose',help="if given, this value will limit the output files to those designed for the given purposes.",choices=('enrol','probe',''))
parser.add_argument('-g','--group',help="if given, this value will limit the output files to those belonging to a particular protocolar group.",choices=('dev','eval','world','optional_world_1','optional_world_2',''))
