Skip to main content
SpringerLink
Log in

Discriminatory Capacity of the Most Representative Phonemes in Spanish: An Evaluation for Forensic Voice Comparison

  • Conference paper
  • First Online:
Advances in Computational Intelligence (MICAI 2016)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10061))

Included in the following conference series:

  • 1387 Accesses

Abstract

In this paper, a study of the discriminatory capacity of the most representative segments for forensic speaker comparison in Mexican Spanish is presented. The study is based on two corpora in order to assess the discriminatory capacity of the fundamental frequency and the three first vocalic formants acoustic parameters for reading and semi-spontaneous speech. We found that the context /sa/ has 73% of discriminatory capacity to classify speakers using the three first formants of the vowel /a/ with a dynamic analysis. We used several statistical techniques and found that the best methodology for the recognition of patterns consists of using linear regression with a quadratic fitting to reduce the number of predictors to a manageable level and apply discriminant analysis on the reduced set. This result is consistent with previous research data despite the methodology for Mexican Spanish had never been used.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The full corpus is available on request to the main author.

  2. 2.

    Centro de Ciencias Aplicadas y Desarrollo Tecnológico.

  3. 3.

    Universidad Nacional Autónoma de México.

  4. 4.

    All statistical analyses were performed with R program. Each statistical analysis was programmed in order to reproduce the methodology proposed in this work.

References

  1. Zipf, G.K., Rogers, F.M.: Phonemes and Variphones in four present-day Romance Languages and Classical Latin from the viewpoint of dynamic Philology. Archives Néerlandaises de Phonétique Experimentale 15, 111–147 (1939)

    Google Scholar 

  2. Navarro, T.: Estudios de Fonología Española. Syracuse University Press, New York (1946)

    Google Scholar 

  3. Alarcos, T.: Estudios de Fonología Española. Gredos, Madrid (1991)

    Google Scholar 

  4. Guirao, M., García, J.: Estudio Estadístico del Español. Consejo Nacional de Investigaciones Científicas y Técnicas, Buenos Aires (1993)

    Google Scholar 

  5. Pérez, E.: Frecuencia de fonemas. E-rthabla, Revista de Tecnologías del habla 1, 1–7 (2003). http://gth-www.die.upm.es/numeros/N1/N1_A4.pdf

  6. Cuétara, J.: Fonética y fonología del habla espontánea de la ciudad de México. Su aplicación en las tecnologías del habla [disertation]. Universidad Nacional Autónoma de México, México (2004)

    Google Scholar 

  7. Pineda, L., Castellanos, H., Cuétara, J., Galescu, L., Juárez, J., Llisterri, J., Pérez, P., Villaseñor, L.: The Corpus DIMEx100: transcription and evaluation. Lang. Resourc. Eval. 44, 347–370 (2010)

    Article  Google Scholar 

  8. Guerra, R.: Estudio estadístico de la sílaba en español. In: Esgueva, M., Cantanero, M. (eds.) Estudios de Fonética, vol. I, pp. 9–112. Consejo Superior de Investigaciones Científicas, Madrid (1983)

    Google Scholar 

  9. McDougall, K.: Speaker-specific formant dynamics: an experiment on Australian English /aI/. Int. J. Speech Lang. Law 11(1), 103–130 (2004)

    Article  Google Scholar 

  10. McDougall, K.: Dynamic features of speech and the characterization of speakers: toward a new approach using formant frequencies. Int. J. Speech Lang. Law 13(1), 89–126 (2006)

    Article  Google Scholar 

  11. Eriksson, E., Sullivan, K.: An investigation of the effectiveness of a Swedish glide+vowel segment for speaker discrimination. Forensic Linguist. 5(1), 51–66 (2008)

    Google Scholar 

  12. Pardo, A., Ruiz, M.A.: SPSS 11. Guía Para el Análisis de Datos. McGraw-Hill, Madrid (2002)

    Google Scholar 

  13. Rencher, A.: Methods of Multivariate Analysis. John Wiley & Sons Inc., Publication, USA (2002)

    Book  MATH  Google Scholar 

  14. Labov, W.: Field methods used by the project on linguistic change and variation. In: Baugh, J., Sherzer, J. (eds.) Language in use: Readings in Sociolinguistics. Prentice Hall, New Jersey (1984)

    Google Scholar 

  15. Turell, M.: La base teórica y metodológica de la variación lingüística. In: Turell, M. (ed.) La Sociolingüística de la Variación. Promociones y Publicaciones Universitarias, Barcelona (1995)

    Google Scholar 

  16. Greisbach, R., Esser, O., Weinstock, C.: Speaker identification by formant contours. In: Braun, A., Köster, J. (eds.) Studies in Forensic Phonetics, pp. 49–55. Wissenschaftlicher Verlag, Trier (1995)

    Google Scholar 

  17. Rose, P.: Long- and short-term within-speaker differences in the formants of Australian hello. In: Braun, A., Köster, J. (eds.) Studies in Forensic Phonetics, pp. 49–55. Wissenschaftlicher Verlag, Trier (1995)

    Google Scholar 

  18. McDougall, K.: Nolan, F: Discrimination of speakers using the formant dynamics of /u:/ in british English. In: Trouvain, J., Barry, W.J. (eds.) Proceeding of the 16th International Congress on Phonetic Sciences, pp. 1825–1828. Universität des Saarlandes, Saarbrücken (2007)

    Google Scholar 

  19. Kinoshita, Y., Ishihara, S., Rose, P.: Exploring the discriminatory potential of F0 distribution parameters in traditional forensic speaker recognition. Int. J. Speech Lang. Law 16(1), 91–111 (2009)

    Article  Google Scholar 

  20. Nolan, F.: The Phonetic Bases of Speech Recognition. Cambridge University Press, Cambridge (1983)

    Google Scholar 

  21. Hollien, H.: The Acoustics of Crime. The New Science of Forensic Phonetics. Plenum Press, New York (1990)

    Google Scholar 

  22. Jiang, M.: Fundamental frequency vector for a speaker identification system. Forensic Linguist. 3(1), 95–106 (1996)

    Google Scholar 

  23. Jessen, M.: Speaker-specific information in voice quality parameters. Forensic Linguist. 4(1), 84–103 (1997)

    Google Scholar 

  24. Foulkes, P., Barron, A.: Telephone speaker recognition amongst members of a close social network. Forensic Linguist. 7(2), 180–198 (2000)

    Google Scholar 

  25. Freund, R., Wilson, W., Sa, P.: Regression Analysis. Statistical Modeling of a Response Variable. Elsevier, Amsterdam (2006)

    Google Scholar 

  26. Boersma, P., Weenink, D.: Praat: doing phonetics by computer [Computer program]. 5.1.25 Version. University of Amsterdam (2010)

    Google Scholar 

Download references

Acknowledgements

Authors want to thank Mrs. Josefina Bolado, Head of the Scientific Paper Translation Department, from División de Investigación at Facultad de Medicina, UNAM, for editing the English-language version of this manuscript.

Author information

Authors and Affiliations

  1. Licenciatura en Ciencia Forense, Facultad de Medicina, UNAM, Circuito de la Investigación Científica SN, CU, 04510, Ciudad de Mexico, Mexico

    Fernanda López-Escobedo

  2. Departamento de Ciencias de la Computación, IIMAS, UNAM, Circuito Escolar SN, CU, 04510, Ciudad de Mexico, Mexico

    Luis Alberto Pineda Cortés

Authors
  1. Fernanda López-Escobedo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luis Alberto Pineda Cortés
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fernanda López-Escobedo .

Editor information

Editors and Affiliations

  1. Instituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City, Mexico

    Grigori Sidorov

  2. Universidad Autónoma Metropolitana, Mexico City, Mexico

    Oscar Herrera-Alcántara

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

López-Escobedo, F., Pineda Cortés, L.A. (2017). Discriminatory Capacity of the Most Representative Phonemes in Spanish: An Evaluation for Forensic Voice Comparison. In: Sidorov, G., Herrera-Alcántara, O. (eds) Advances in Computational Intelligence. MICAI 2016. Lecture Notes in Computer Science(), vol 10061. Springer, Cham. https://doi.org/10.1007/978-3-319-62434-1_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-62434-1_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-62433-4

  • Online ISBN: 978-3-319-62434-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation