Abstract
The suitability of voiceless fricative spectra for forensic voice comparison is explored within a Likelihood Ratio-based framework. Non-contemporaneous landline telephone recordings of 99 male Japanese speakers are compared using only tokens of their voiceless alveolo-patalal fricative [6]. A subset of mean-cepstrally-subtracted LPC CCs from the fricative spectrum from dc to 5 kHz is used. GMM/UBM and multivariate likelihood ratios are extracted for the 99 target and 4851 non-target trials, and fused with logistic regression. An EER of 7.4% and log-LR cost of 0.26 is demonstrated. It is concluded that the [6] spectrum does have some individualising potential.
Original language | English |
---|---|
Pages | 5900-5903 |
DOIs | |
Publication status | Published - 2011 |
Event | International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011) - Prague Czech Republic Duration: 1 Jan 2011 → … |
Conference
Conference | International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011) |
---|---|
Period | 1/01/11 → … |