An investigation of the effectiveness of a Swedish glide + vowel segment for speaker discrimination


  • Erik Johannes Eriksson Umeå University
  • Kirk Patrick Haig Sullivan Umeå University



formant dynamics, speaker identity, speaker separation, glide vowel, linear discriminant analysis


Research based on the Australian English diphthong and the British English segment vowel+/r/+vowel has shown that the dynamics of F1, F2, and F3 frequencies can be used for speaker discrimination. This study investigates whether this method can be applied to Swedish. Five male speakers of Swedish were recorded reading a newspaper article that contained seven glide+vowel target tokens. F1, F2, F3, and F4 frequencies were examined at equidistant time-normalized intervals through these tokens. Discriminant analysis based on six predictors from all four formants yielded a classification rate of 88%. This is comparable to earlier research based on a larger predictor set and with recordings that were more controlled by the researcher than the ones used in this study. The present study confirms the power of this approach for speaker discrimination.

Author Biographies

Erik Johannes Eriksson, Umeå University

Erik Eriksson has a Masters degree in Cognitive Science from Umeå University and completed his PhD on Factors in Speaker Recognition in May 2007.

Kirk Patrick Haig Sullivan, Umeå University

Kirk P H Sullivan is a docent in Phonetics in the Department of Language Studies at Umeå University, Sweden. He is a graduate of the Universities of Wales, Loughborough and Southampton and was a post-doctoral fellow at the University of Otago, New Zealand, prior to taking his current position in 1994. His research interests include second and foreign language acquisition and forensic linguistics.



How to Cite

Eriksson, E. J., & Sullivan, K. P. H. (2008). An investigation of the effectiveness of a Swedish glide + vowel segment for speaker discrimination. International Journal of Speech, Language and the Law, 15(1), 51–66.