ComputeJFAStatsMain.cpp

Go to the documentation of this file.
00001 /*
00002 This file is part of LIA_RAL which is a set of software based on ALIZE
00003 toolkit for speaker recognition. ALIZE toolkit is required to use LIA_RAL.
00004 
00005 LIA_RAL project is a development project was initiated by the computer
00006 science laboratory of Avignon / France (Laboratoire Informatique d'Avignon -
00007 LIA) [http://lia.univ-avignon.fr <http://lia.univ-avignon.fr/>]. Then it
00008 was supported by two national projects of the French Research Ministry:
00009         - TECHNOLANGUE program [http://www.technolangue.net]
00010         - MISTRAL program [http://mistral.univ-avignon.fr]
00011 
00012 LIA_RAL is free software: you can redistribute it and/or modify
00013 it under the terms of the GNU Lesser General Public License as
00014 published by the Free Software Foundation, either version 3 of
00015 the License, or any later version.
00016 
00017 LIA_RAL is distributed in the hope that it will be useful,
00018 but WITHOUT ANY WARRANTY; without even the implied warranty of
00019 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
00020 GNU Lesser General Public License for more details.
00021 
00022 You should have received a copy of the GNU Lesser General Public
00023 License along with LIA_RAL.
00024 If not, see [http://www.gnu.org/licenses/].
00025 
00026 The LIA team as well as the LIA_RAL project team wants to highlight the
00027 limits of voice authentication in a forensic context.
00028 The "Person Authentification by Voice: A Need of Caution" paper
00029 proposes a good overview of this point (cf. "Person
00030 Authentification by Voice: A Need of Caution", Bonastre J.F.,
00031 Bimbot F., Boe L.J., Campbell J.P., Douglas D.A., Magrin-
00032 chagnolleau I., Eurospeech 2003, Genova].
00033 The conclusion of the paper of the paper is proposed bellow:
00034 [Currently, it is not possible to completely determine whether the
00035 similarity between two recordings is due to the speaker or to other
00036 factors, especially when: (a) the speaker does not cooperate, (b) there
00037 is no control over recording equipment, (c) recording conditions are not
00038 known, (d) one does not know whether the voice was disguised and, to a
00039 lesser extent, (e) the linguistic content of the message is not
00040 controlled. Caution and judgment must be exercised when applying speaker
00041 recognition techniques, whether human or automatic, to account for these
00042 uncontrolled factors. Under more constrained or calibrated situations,
00043 or as an aid for investigative purposes, judicious application of these
00044 techniques may be suitable, provided they are not considered as infallible.
00045 At the present time, there is no scientific process that enables one to
00046 uniquely characterize a persones voice or to identify with absolute
00047 certainty an individual from his or her voice.]
00048 
00049 Copyright (C) 2004-2010
00050 Laboratoire d'informatique d'Avignon [http://lia.univ-avignon.fr]
00051 LIA_RAL admin [alize@univ-avignon.fr]
00052 Jean-Francois Bonastre [jean-francois.bonastre@univ-avignon.fr]
00053 */
00054 
00055 
00056 #include <iostream>
00057 
00058 #include "liatools.h"
00059 #include "ComputeJFAStats.h"
00060 
00061 using namespace alize;
00062 using namespace std;
00063 
00064 int main(int argc, char* argv[]) {
00065         ConfigChecker cc;
00066         try {
00067                 // Needed params
00068                 cc.addStringParam("ndxFilename",true,true,"NDX of multiple GMM speaker recordings");
00069                 cc.addStringParam("inputWorldFilename",true,true,"the world model file");
00070                 cc.addStringParam("saveMatrixFormat",true,true,"matrix format: DB (binary) or DT (ascii)");
00071                 cc.addStringParam("saveMatrixFilesExtension",true,true,"matrix file extension");
00072                 
00073                 
00074 
00075                 // Optionnal
00076                 cc.addStringParam("loadMatrixFormat",false,true,"matrix format: DB (binary) or DT (ascii)");
00077                 cc.addStringParam("nullOrderStatSpeaker",false,true,"Name of the Null order speaker stat matrix to store");
00078                 cc.addStringParam("nullOrderStatSession",false,true,"Name of the Null order session stat matrix to store");
00079                 cc.addStringParam("firstOrderStatSpeaker",false,true,"Name of the First order speaker stat matrix to store");
00080                 cc.addStringParam("firstOrderStatSession",false,true,"Name of the First order session stat matrix to store");
00081                 
00082 
00083 
00084                 // Insertion of config compatibility rules
00085                 CmdLine cmdLine(argc, argv);
00086                 if (cmdLine.displayHelpRequired()){
00087                         cout << "****************************************" << endl;
00088                         cout << "********** ComputeJFAStats.exe ************" << endl;
00089                         cout << "****************************************" << endl;
00090                         cout << endl;
00091                         cout << "Compute sufficient statisitc for Joint Factor Analysis" << endl;
00092                         cout <<endl<<cc.getParamList()<<endl;
00093                         return 0;  
00094                 }
00095         if (cmdLine.displayVersionRequired()){
00096           cout <<"Version 2.0 Mistral Package"<<endl;
00097         } 
00098 
00099                 Config tmp;
00100                 cmdLine.copyIntoConfig (tmp);
00101                 Config config;
00102                 if (tmp.existsParam("config")) config.load(tmp.getParam("config"));
00103                 cmdLine.copyIntoConfig(config);
00104                 cc.check(config);
00105                 debug=config.getParam_debug();  
00106                 if (config.existsParam("verbose"))verbose=config.getParam("verbose").toBool();else verbose=false;
00107                 if (verbose) verboseLevel=1;else verboseLevel=0;
00108                 if (config.existsParam("verboseLevel"))verboseLevel=config.getParam("verboseLevel").toLong();
00109                 if (verboseLevel>0) verbose=true;               
00110                 if (cmdLine.displayHelpRequired()) {cout << cc.getParamList() << endl;} 
00111                 ComputeJFAStats(config);        
00112                 }
00113         catch (Exception& e) {cout << e.toString() << cc.getParamList() << endl;}
00114 if (debug) {
00115 }
00116 return 0;
00117 }