Forensic voice comparison and the paradigm shift.

We are in the midst of a paradigm shift in the forensic comparison sciences. The new paradigm can be characterised as quantitative data-based implementation of the likelihood-ratio framework with quantitative evaluation of the reliability of results. The new paradigm was widely adopted for DNA profile comparison in the 1990s, and is gradually spreading to other branches of forensic science, including forensic voice comparison. The present paper first describes the new paradigm, then describes the history of its adoption for forensic voice comparison over approximately the last decade. The paradigm shift is incomplete and those working in the new paradigm still represent a minority within the forensic-voice-comparison community.

[1]  Phil Rose,et al.  A response to the UK position statement on forensic speaker comparison , 2009 .

[2]  Andrzej Drygajlo,et al.  Aural and automatic forensic speaker recognition in mismatched conditions , 2005 .

[3]  Philip Rose,et al.  The Technical Comparison of Forensic Voice Samples , 2003 .

[4]  Colin Aitken,et al.  The use of statistics in forensic science , 1991 .

[5]  F Botti,et al.  On compensation of mismatched recording conditions in the Bayesian approach for forensic automatic speaker recognition. , 2004, Forensic science international.

[6]  A. P. A. Broeders,et al.  FORENSIC SPEECH AND AUDIO ANALYSIS FORENSIC LINGUISTICS , 2001 .

[7]  Eliathamby Ambikairajah,et al.  FM features for automatic forensic speaker recognition , 2008, INTERSPEECH.

[8]  David A. van Leeuwen,et al.  An Introduction to Application-Independent Evaluation of Speaker Recognition Systems , 2007, Speaker Classification.

[9]  David A. van Leeuwen,et al.  Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006 , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  Phil Rose,et al.  Technical forensic speaker recognition: Evaluation, types and testing of evidence , 2006, Comput. Speech Lang..

[11]  John Buckleton.  A Framework for Interpreting Evidence , 2004 .

[12]  Hirotaka Nakasone,et al.  Forensic automatic speaker recognition , 2001, Odyssey.

[13]  Douglas A. Reynolds,et al.  A Tutorial on Text-Independent Speaker Verification , 2004, EURASIP J. Adv. Signal Process..

[14]  Philip Rose,et al.  Forensic Speaker Recognition at the Beginning of the Twenty-First Century - An Overview and a Demonstration , 2005 .

[15]  Didier Meuwly.  Reconnaissance de locuteurs en sciences forensiques: l'apport d'une approche automatique , 2000 .

[16]  J A Lambert,et al.  The impact of the principles of evidence interpretation on the structure and content of statements. , 2000, Science & justice : journal of the Forensic Science Society.

[17]  Philip Rose,et al.  Forensic speaker recognition in Chinese: a multivariate likelihood ratio discrimination on /i/ and /y/ , 2008, INTERSPEECH.

[18]  Franco Taroni,et al.  Statistics and the Evaluation of Evidence for Forensic Scientists , 2004 .

[19]  Yuko Kinoshita.  Testing realistic forensic speaker identification in Japanese: a likelihood ratio-based approach using formants , 2007 .

[20]  G. Morrison.  Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongs. , 2009, The Journal of the Acoustical Society of America.

[21]  Ton Broeders,et al.  Forensic Speech and Audio Analysis Forensic Linguistics 1998-2001 , 2001 .

[22]  Javier Ortega-Garcia,et al.  Robust estimation, interpretation and assessment of likelihood ratios in forensic speaker recognition , 2006, Comput. Speech Lang..

[23]  Doroteo Torre Toledano,et al.  Emulating DNA: Rigorous Quantification of Evidential Weight in Transparent and Testable Forensic Speaker Recognition , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[24]  Roger K. Moore.  Computer Speech and Language , 1986 .

[25]  Geoffrey Stewart Morrison.  Forensic voice Comparison using likelihood ratios based on Polynomial curves fitted to the formant trajectories of Australian English , 2009 .

[26]  Richard S. Frank,et al.  The Theory of Interpreting Scientific Transfer Evidence , 1990 .

[27]  Reva Schwartz.  Voiceprints in the United States - Why they won't go away , 2006 .

[28]  David Lucy,et al.  Introduction to Statistics for Forensic Scientists , 2005 .

[29]  Niko Brümmer,et al.  Application-independent evaluation of speaker detection , 2006, Comput. Speech Lang..

[30]  Geoffrey Stewart Morrison,et al.  Automatic-type calibration of traditionally derived likelihood ratios: forensic analysis of australian English /o/ formant trajectories , 2008, INTERSPEECH.

[31]  David Lindley,et al.  Probability and the Law , 1977 .

[32]  D. Meuwly,et al.  Reconnaissance automatique de locuteurs en sciences forensiques: Modelisation de la variabilite intralocuteur et interlocuteur , 2000 .

[33]  W. Thompson,et al.  Interpretation of statistical evidence in criminal trials , 1987 .

[34]  D. Balding.  Weight-of-Evidence for Forensic DNA Profiles , 2005 .

[35]  G. Morrison.  Comments on Coulthard & Johnson's (2007) portrayal of the likelihood-ratio framework , 2009 .

[36]  David A. van Leeuwen,et al.  Results of the 2003 NFI-TNO forensic speaker recognition evaluation , 2004, Odyssey.

[37]  David L. Faigman,et al.  Modern scientific evidence : the law and science of expert testimony , 2006 .

[38]  D Meuwly,et al.  Forensic individualisation from biometric data. , 2006, Science & justice : journal of the Forensic Science Society.

[39]  Peter French,et al.  Position Statement concerning use of impressionistic likelihood terms in forensic speaker comparison cases, with a foreword by Peter French & Philip Harrison , 2007 .

[40]  I. Evett,et al.  A hierarchy of propositions: deciding which level to address in casework , 1998 .

[41]  I. W. Evett,et al.  Towards a uniform framework for reporting opinions in forensic science casework , 1998 .

[42]  Yuko Kinoshita.  Does Lindley's LR estimation formula work for speech data? Investigation using long-term f0 , 2005 .

[43]  Michael Jessen,et al.  Forensic speaker verification using formant features and Gaussian mixture models , 2008, INTERSPEECH.

[44]  Didier Meuwly,et al.  The inference of identity in forensic speaker recognition , 2000, Speech Commun..

[45]  Philip Rose,et al.  Strength of forensic speaker identification evidence : multispeaker formant and cepstrum-based segmental discrimination with a Bayesian likelihood ratio as threshold , 2002 .

[46]  T. Kuhn,et al.  The Structure of Scientific Revolutions. , 1964 .

[47]  Daniel Ramos Castro.  Extended Abstract for Best Ph.D. Thesis Award: Forensic Evaluation of the Evidence Using Automatic Speaker Recognition Systems , 2007 .

[48]  J. Robertson.  ‘Forensic Evidence Goes on Trial’ , 2009 .

[49]  Philip Rose.  Forensic Speaker Identification , 2002 .

[50]  Philip Rose,et al.  Differences and Distinguishability in the Acoustic Characteristics of Hello in Voices of Similar-sounding Speakers - a Forensic Investigation , 1999 .

[51]  Claude Roux,et al.  Statistics and the Evaluation of Evidence for Forensic Scientists, by Colin G. G. Aitken and Franco Taroni 2nd edition. John Wiley and Sons, 2004. , 2006 .

[52]  Didier Meuwly,et al.  Forensic speaker recognition based on a Bayesian framework and Gaussian mixture modelling (GMM) , 2001, Odyssey.

[53]  J. Buckleton,et al.  Forensic DNA Evidence Interpretation , 2004 .

[54]  Ian W. Evett,et al.  Statistical analysis of STR data , 1996 .

[55]  J. Koehler,et al.  The Coming Paradigm Shift in Forensic Identification Science , 2005, Science.

[56]  A. Maehly,et al.  Forensic Science Progress , 2011 .

[57]  Ian W. Evett,et al.  Interpreting DNA Evidence: A Review , 2003 .

[58]  Didier Meuwly,et al.  Forensic Speaker Recognition Using Gaussian Mixture Models and a Bayesian Framework , 1998 .

[59]  Law. Policy.  Executive Summary of the National Academies of Science Reports, Strengthening Forensic Science in the United States: A Path Forward , 2009 .