Likelihood ratio-based forensic voice comparison with higher level features: research and reality

摘要

Examples are given of forensic voice comparison with higher level features in real-world cases and research. A pilot experiment relating to estimation of strength of evidence in forensic voice comparison is described which explores the use of higher-level features extracted over a disyllabic word as a whole, rather than over individual monosyllables as conventionally practiced. The trajectories of the first three formants and tonal FO of the hexaphonic disyllabic Cantonese word daihyat 'first' from controlled but natural non-contemporaneous recordings of 23 male speakers are modeled with polynomials, and multivariate likelihood ratios estimated from their coefficients. Evaluation with the log likelihood ratio cost validity metric C_(llr) shows an optimum performance is obtained, surprisingly, with lower order polynomials, with F2 requiring a cubic fit, and F1 and F3 quadratic. Fusion of F-pattern and tonal F0 results in considerable improvement over the individual features, reducing the C_(llr) to ca. 0.1. The forensic potential of the daihyat data is demonstrated by fusion with three other Cantonese higher-level features: the F-pattern of short-term F0, and syllabic nasal cepstral spectrum, which reduces the C_(llr) still further to 0.03. Important pros and cons of higher-level features and likelihood ratios are discussed, the latter illustrated with data from Japanese, and three varieties of English in real forensic casework.