More is better: likelihood ratio-based forensic voice comparison with vocalic segmental cepstra frontends

Authors

  • Phil Rose Australian National University

DOI:

https://doi.org/10.1558/ijsll.v20i1.77

Keywords:

forensic voice comparison, likelihood ratio, vowel spectra, cepstrum

Abstract

The suitability of vowel cepstral spectra for forensic voice comparison is explored within a likelihood ratio-based framework, and non-technical explanations provided for some basic concepts of cepstral analysis and forensic voice comparison. Non-contemporaneous landline telephone recordings of 297 male Japanese speakers are compared using only two replicates per recording of each of their five read-out vowels. 14 cepstrally-mean-subtracted LPC cepstral coefficients modelling the spectral shape to 5 kHz are used as features. When evaluated intrinsically with kernel density multivariate likelihood ratios, all 297 same-speaker comparisons are correctly discriminated as coming from the same speaker, and only 173 of the 43,956 different-speaker comparisons (0.4%) are incorrectly evaluated as coming from the same speaker. The log-likelihood ratio cost for this comparison is very low at 0.013. Fusion with a speaker’s long-term spectral data marginally improves the different-speaker error rate to 0.27% and the log-likelihood ratio cost to 0.009. It is concluded that the approach warrants further examination.

Author Biography

Phil Rose, Australian National University

Phil Rose was Reader at the Australian National University, where he taught Phonetics and Chinese Linguistics for 30 years. He has been a British Academy visiting professor at the University of Edinburgh’s Joseph Bell Centre for Forensic Statistics and Legal Reasoning, is chairman of the Forensic Speech Science Committee of the Australasian Speech Science and Technology Association and a member of the Australian Academy of Forensic Sciences. His 2002 book pioneered the application of the likelihood ratio of Bayes’ Theorem to traditional forensic voice comparison, thus bringing it in line with forensic DNA profiling. He has done forensic voice comparison case-work on Australian English and varieties of Chinese for nearly 20 years and was last seen teaching courses on Chinese Phonetics and Forensic Voice Comparison in Cantonese at the Hong Kong University of Science and Technology.

Published

2013-07-09

How to Cite

Rose, P. (2013). More is better: likelihood ratio-based forensic voice comparison with vocalic segmental cepstra frontends. International Journal of Speech, Language and the Law, 20(1), 77–116. https://doi.org/10.1558/ijsll.v20i1.77

Issue

Section

Articles