ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Forensic speaker verification using formant features and Gaussian mixture models

Timo Becker, Michael Jessen, Catalin Grigoras

A new method for speaker verification based on formant features is presented. A UBM-GMM verification system is applied to semi-automatically extracted formant features. Speaker-specific vocal tract configurations, including the speakers' variability, are incorporated in the speaker models. Speaker comparisons are expressed as likelihood ratios (the ratio of similarity to typicality). F1, F2 and F3 values all enable speakers to be distinguished with a low error rate. The corresponding bandwidths further lower the error rate.


doi: 10.21437/Interspeech.2008-432

Cite as: Becker, T., Jessen, M., Grigoras, C. (2008) Forensic speaker verification using formant features and Gaussian mixture models. Proc. Interspeech 2008, 1505-1508, doi: 10.21437/Interspeech.2008-432

@inproceedings{becker08_interspeech,
  author={Timo Becker and Michael Jessen and Catalin Grigoras},
  title={{Forensic speaker verification using formant features and Gaussian mixture models}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1505--1508},
  doi={10.21437/Interspeech.2008-432}
}