Long-term formant distribution as a forensic-phonetic feature.
Michael Erik Jessen, Timo Becker · The Journal of the Acoustical Society of America · 2010
With the long-term formant distribution (LTF) method [F. Nolan and C. Grigoras, Int. J. Speech, Lang. Law 12, 143–173 (2005)], manually corrected LPC-based formant tracks are extracted over all vocalic portions of the recording of a speaker in which the formants F2 and F3 are sufficiently well-structured. LTF analysis has been successfully added to the inventory of phonetic features that are used in voice comparison casework. Current research has highlighted a number of advantages of the LTF method, including high inter-expert reliability (different phoneticians arrive at highly consistent results), anatomical motivation (long-term F2 and F3 are negatively correlated with speaker height), and language independence (LTF patterns in different languages—so far, German, Russian, and Albanian—do not differ significantly). Presently, quantitative measures of inter-individual variation in case data are investigated, including equal error rates and calibrated likelihood ratios based on Gaussian mixture modeling of the formant tracking raw data [Becker et al., Proc. Interspeech, 1505–1508, 2008]. The final inter-individual variation results will be presented, along with results on how the LTF method compares to automatic speaker recognition, which is applied to the same data.