Publications
- A. Drygajlo, D. Meuwly, and A. Alexander, ``Statistical Methods and Bayesian Interpretation of Evidence in Forensic Automatic Speaker Recognition,'' in Proc. Eurospeech 2003, Geneva, Switzerland, 2003, pp. 689-692
- D.Meuwly, A. Alexander, A. Drygajlo, and F. Botti, ``Polyphone-IPSC: A Shared Speakers Database for Evaluation of Forensic-automatic Speaker Recognition Systems,'' in Forensic Science International, vol. 136. Istanbul, Turkey: Elsevier, September 2003, p. 367
- A. Alexander and A. Drygajlo, ``Scoring and Direct Methods for the Interpretation of Evidence in Forensic Speaker Recognition,'' in Proceedings of 8th International Conference on Spoken Language Processing (ICSLP), Jeju, Korea, 2004
- A. Alexander, F. Botti, and A. Drygajlo, ``Handling Mismatch in Corpus-Based Forensic Speaker Recognition,'' in Proceedings of 2004: A Speaker Odyssey, Toledo, Spain, May 2004, pp. 69-74
- F. Botti, A. Alexander, and A. Drygajlo, ``On Compensation of Mismatched Recording Conditions in the Bayesian Approach for Forensic Automatic Speaker Recognition,'' Forensic Science International, Elsevier. Volume 146, Supplement 1, 2 December 2004, Pages S101-S106
- F. Botti., A. Alexander, and A. Drygajlo, ``An Interpretation Framework for the Evaluation of Evidence in Forensic Automatic Speaker Recognition with Limited Suspect Data,'' in Proceedings of 2004: A Speaker Odyssey, Toledo, Spain, 2004, pp. 63-68
- F. Botti, A. Alexander, and A. Drygajlo, ``Evaluation of Evidence in Forensic Speaker Recognition with a Questioned recording and a Single suspect's Recording,'' in Proceedings of the 3rd European Academy of Forensic Science Meeting,Forensic Science International, vol. 136.Istanbul, Turkey: Elsevier, September 2003, p. 365-366
- A. Alexander, F. Botti, D. Dessimoz, and A. Drygajlo, "The effect of mismatched recording conditions on human and automatic speaker recognition in forensic applications", Forensic Science International, Elsevier, Volume 146, Supplement 1, 2 December 2004, Pages S95-S99
- A. Alexander, D. Dessimoz, F. Botti, A. Drygajlo, "On the Use of
Auditory and Automatic Systems to Handle Mismatched Conditions in
Forensic Speaker Recognition". International Journal of Speech,
Language and the Law, Vol. 12(2), 2005, pp 214-234
- M. Arcienega, A. Alexander, P. Zimmerman and A. Drygajlo, 'A Bayesian network approach combining pitch and spectral envelope features
to reduce channel mismatch in speaker verification and forensic
speaker recognition', Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology, September 2005, Lisbon, Portugal pp. 2009-2012
- Anil Alexander, Ph.D thesis (no. 3367), November 2005, Swiss Federal Institute of Technology, Lausanne, 'Forensic automatic speaker recognition using Bayesian interpretation and statistical compensation for mismatched conditions'.
Here is the- Full PhD Thesis (2.3 MB in pdf format)
- Title page
- Abstract
- Acknowledgements
- Table of contents
- Bibliography
- Chapter: Conclusions
- P. Prodanov, A. Drygajlo, J. Richiardi and A. Alexander, (2007). 'Low-level grounding in a multimodal mobile service robot conversational system using graphical models', Journal of Intelligent Service Robotics, Springer Berlin / Heidelberg, doi = {10.1007/s11370-006-0001-9}, URL
-
A. Alexander, Forensic automatic speaker recognition using Bayesian interpretation and statistical compensation for mismatched conditions , (adapted PhD Abstract) International Journal of Speech,
Language and the Law, pp 145-147, Vol. 14(1), 2007,
- A. Alexander and J. K. McElveen, primer, 'Approaches to Speaker Recognition: A Primer' A short and simple introduction to speaker recognition applied to forensic applications, Clarifying Technologies Ltd, 2007.
- A. Alexander and J. K. McElveen, extended abstract, 'An open-standard file format for forensic audio' , in Proceedings, IAFPA 2006, Department of Linguistics, Goteborg University, presented at the International Association for Forensic Phonetics and Acoustics (IAFPA) Annual Conference, July 2006, Goteborg, Sweden.
Here are the presentation slides in pdf. - Invited seminar talk slides, ' A Bayesian approach to forensic speaker recognition' , presented at the Winter School on Forensic Sciences, Applied Statistics Unit, Indian Statistical Institute, Kolkata February 2006
- Poster, ' A Bayesian network approach combining pitch and spectral envelope features to reduce channel mismatch in speaker verification and forensic speaker recognition' , presented at Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology, September 2005, Lisbon, Portugal.
- Abstract, A methodology for the creation of a forensic speaker recognition database to handle mismatched conditions and presentation, presented at the International Association for Forensic Phonetics and Acoustics (IAFPA) Annual Conference, August 2005 in Marrakesh, Morocco.
- Presentation, 'On the use of auditory and automatic systems to handle mismatched conditions in forensic speaker recognition' presented at the International Association for Forensic Phonetics and Acoustics (IAFPA) Annual Conference 2004 in Helsinki.
Here's the [abstract book] - Poster presented at International Conference on Spoken Language Processing (ICSLP), 2004, Jeju, Korea, "Scoring and Direct Methods for the Interpretation of Evidence in Forensic Speaker Recognition
- Abstract 'On estimation of the strength of evidence in forensic speaker recognition' at The Fifth International Conference on Forensic Statistics Isola di San Servolo, Venice, Italy August 30 - September 2, 2002. Won an honourable mention (second prize) in the Best Poster category.
- Presentation, 'Handling Mismatch in Corpus-Based Forensic Speaker Recognition' presented at 2004, A Speaker Odyssey, Toledo, Spain
- Here are some supervised student projects, tutorials, software, FAQ's and other odds and ends.
- Here is a selection of references (and bibtex) useful in forensic speaker recognition, some of which have been used in the above papers
Short articles, abstracts, posters & presentations
Student projects, tutorials, software, presentations & demos
Bibliography
Simply put:
The pdf's are provided here for your personal reading. Please respect the copyrights of the conferences and publishers. - Full PhD Thesis (2.3 MB in pdf format)