Abstract
Speaker identification can be summarized as the classification task that determines if two voices were spoken by the same person or not. It is a thoroughly studied topic, since it has applications in many fields. One is forensic phonetics, considered very hard since the expert has to face ambient noise, very short recordings, interference, loss of signal, and so on. For decades, these problems have been tackled by experts using their listening abilities, and each of them might represent a research area on its own. The use of semi-automatic techniques may represent a modern alternative to the subjective evaluation of experts, that may enforce fairness of the classification procedure. In a nutshell, we use the differences in speech of a set of different voices to build a population model, and the suspected person’s voice to build a speaker model. The classification is carried out evaluating the similarity of a further speech sample (the evidence) with respect to the models. Preliminary evaluations shown that our approach reaches promising results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
With the financial support of the Prevention and Fight against Crime Program of the European Union European Commission - Directorate - General Justice, Freedom and Security. A project funded by the EU ISEC 2010. Agreement number: HOME/2010/ISEC/MO/4000001759.
References
Federico, A., Ibba, G., Paoloni, A.: A new automated method for reliable speaker identification and verification over telephone channel. In: ICASSP, p. 1457 (1987)
Alzqhoul, E.A.S., Nair, B.B.T., Guillemin, B.J.: Comparison between speech parameters for forensic voice comparison using mobile phone speech. In: Speech Science and Conference 2014 (2014)
Becker, T., Jessen, M., Grigoras, C.: Forensic speaker verification using formant features and Gaussian mixture models. In: INTERSPEECH, pp. 1505–1508. ISCA (2008)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press Inc., New York (1995)
Grigoras, C.: Forensic voice analysis based on long term formant distributions. In: 4th European Academy of Forensic Science Conference (2006)
Calvani, F.: Il problema dell’errore di assegnazione nel riconoscimento del parlatore. Tesi di laurea in Matematica, Universit Tor Vergata di Roma (1996)
Calvani, F.: Analisi critica di metodi per la classificazione del parlatore nelle scienze forensi. Tesi di laurea in Matematica, Universit Tor Vergata di Roma (1998)
Drygajlo, D.: Forensic automatic speaker recognition. IEEE Sig. Process. Mag. 24, 132–135 (2007)
Drygajlo, A., Meuwly, D., Alexander, A.: Statistical methods and Bayesian interpretation of evidence in forensic automatic speaker recognition. In: EUROSPEECH 2003, Geneva, Switzerland, pp. 689–692 (2003)
Koenig, B.E.: Selected topics in forensic voice identification. Crime Lab. Dig. 20(4), 78–81 (1993)
Mathan, L., Bimbot, F., Magrin-Chagnolleau, I.: Second-order statistical measures for text-independent speaker identification. Speech Commun. 17, 177–192 (1995)
Falcone, M., Paoloni, A., De Sario, N.: IDEM: a software tool to study vowel formant in speaker identification. In: Proceedings of the ICPHS 1995, Stockholm, vol. 3, pp. 294–297 (1995)
Ferilli, S., Leuzzi, F., Rotella, F.: Cooperating techniques for extracting conceptual taxonomies from text. In: Proceedings of the Workshop on Mining Complex Patterns at AI*IA XIIth Conference (2011)
Ferilli, S., Leuzzi, F., Rotella, F.: A run length smoothing-based algorithm for non-Manhattan document segmentation. In: Proceedings of Convegno del Gruppo Italiano Ricercatori in Pattern Recognition (2012)
Furui, S.: Digital Speech Processing, Synthesis and Recognition. Marcel Dekker Inc., New York (1989)
Paoloni, A., Ibba, G.: Analisi delle voci: il parlatore ignoto. Poste e Telecomunicazioni, pp. 14–25 (1993)
Ghizzoni, A.: Il problema dell’identificazione del parlatore nelle scienze forensi: modelli, metodi di classificazione e analisi dei dati. Tesi di laurea in Matematica, Universit Tor Vergata di Roma (1999)
Grimaldi, M., dApolito, S., Gili Fivela, B., Sigona, F.: Illusione e scienza nella fonetica forense: una sintesi. Mondo digitale (2014)
Kersta, L.J.: Voiceprint identification. Nature 196, 1253–1257 (1962)
Leuzzi, F., Ferilli, S., Rotella, F.: Improving robustness and flexibility of concept taxonomy learning from text. In: Appice, A., Ceci, M., Loglisci, C., Manco, G., Masciari, E., Ras, Z.W. (eds.) NFMCP 2012. LNCS, vol. 7765, pp. 170–184. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37382-4_12
Leuzzi, F., Ferilli, S., Rotella, F.: ConNeKTion: a tool for handling conceptual graphs automatically extracted from text. In: Catarci, T., Ferro, N., Poggi, A. (eds.) IRCDL 2013. CCIS, vol. 385, pp. 93–104. Springer, Heidelberg (2014). doi:10.1007/978-3-642-54347-0_11
Leuzzi, F., Ferilli, S., Rotella, F.: A relational unsupervised approach to author identification. In: Appice, A., Ceci, M., Loglisci, C., Manco, G., Masciari, E., Ras, Z.W. (eds.) NFMCP 2013. LNCS, vol. 8399, pp. 214–228. Springer, Cham (2014). doi:10.1007/978-3-319-08407-7_14
Lindh, J.: Preliminary F0 statistics and forensic phonetics. In: Lindh, J., Eriksson, A. (eds.) Annual Conference of IAFPA, Department of Linguistics, Gteborg University (2006)
Nolan, F.: Speaker recognition and forensic phonetics. In: The Handbook of Phonetic Sciences (1997)
Nolan, F., Grigoras, C.: A case for formant analysis in forensic speaker identification. Int. J. Speech Lang. Law 12(2), 143 (2005)
Rose, P.: Forensic Speaker Identification. Taylor & Francis London, New York (2002)
Paoloni, A., Falcone, M., Federico, A.: The parametric approach in forensic speaker recognition. In: Proceedings of COST 250 Workshop on Speaker Recognition by Man and Machine: Directions for Forensic Applications, pp. 45–51 (1998)
Rosati, F.: Sperimentazione del metodo bootstrap nel problema del riconoscimento del parlatore. Tesi di laurea in Matematica, Universit Tor Vergata di Roma (2001)
Rossi, C.: Il problema di decisione dell’identificazione del parlatore. Caratterizzazione del parlatore, pp. 173–176 (1996)
Rossi, C.: Classification and decision making in forensic sciences: the speaker identification problem. In: Rizzi, A., Vichi, M., Bock, H. (eds.) Advances in Data Sciences and Calssification, pp. 647–654. Springer, Heidelberg (1998). doi:10.1007/978-3-642-72253-0_88
Rotella, F., Ferilli, S., Leuzzi, F.: An approach to automated learning of conceptual graphs from text. In: Ali, M., Bosse, T., Hindriks, K.V., Hoogendoorn, M., Jonker, C.M., Treur, J. (eds.) IEA/AIE 2013. LNCS, vol. 7906, pp. 341–350. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38577-3_35
Rotella, F., Ferilli, S., Leuzzi, F.: A domain based approach to information retrieval in digital libraries. In: Agosti, M., Esposito, F., Ferilli, S., Ferro, N. (eds.) IRCDL 2012. CCIS, vol. 354, pp. 129–140. Springer, Heidelberg (2013). doi:10.1007/978-3-642-35834-0_14
Rotella, F., Leuzzi, F., Ferilli, S.: Learning and exploiting concept networks with connektion. Appl. Intell. 42(1), 87–111 (2015)
Forte, A., Rossi, C., Bove, T., Giua, P.E.: Un metodo statistico per il riconoscimento del parlatore basato sull’analisi delle formanti. Statistica LXII, 177–192
Furui, S., Matsui, T.: Adaptation of tied mixture based phoneme models for text-prompted speaker verification. In: ICASSP, pp. 125–128 (1994)
Wand, M.P., Jones, M.C.: Kernel Smoothing. Monographs on Statistics and Applied Probability. Chapman & Hall/CRC, Boca Raton, London, New York (1995)
Wolf, J.J.: Efficient acoustic parameters for speaker recognition. J. Acoust. Soc. Am. 51(6), 2044–2056 (1972)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Leuzzi, F. et al. (2017). A Statistical Approach to Speaker Identification in Forensic Phonetics. In: Appice, A., Ceci, M., Loglisci, C., Masciari, E., Raś, Z. (eds) New Frontiers in Mining Complex Patterns. NFMCP 2016. Lecture Notes in Computer Science(), vol 10312. Springer, Cham. https://doi.org/10.1007/978-3-319-61461-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-61461-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61460-1
Online ISBN: 978-3-319-61461-8
eBook Packages: Computer ScienceComputer Science (R0)