TY - GEN
T1 - Automatic-type calibration of traditionally derived likelihood ratios
T2 - 9th Annual Conference of the International Speech Communication Association
AU - Morrison, Geoffrey Stewart
AU - Kinoshita, Yuko
N1 - Copyright © 2008 ISCA
PY - 2008
Y1 - 2008
N2 - A traditional-style phonetic-acoustic forensic-speaker-recognition analysis was conducted on Australian English /o/ recordings. Different parametric curves were fitted to the formant trajectories of the vowel tokens, and cross-validated likelihood ratios were calculated using a single-stage generative multivariate kernel density formula. The outputs of different systems were compared using C llr, a metric developed for automatic speaker recognition, and the cross-validated likelihood ratios were calibrated using a procedure developed for automatic speaker recognition. Calibration ameliorated some likelihood-ratio results which had offered strong support for a contrary-to-fact hypothesis.
AB - A traditional-style phonetic-acoustic forensic-speaker-recognition analysis was conducted on Australian English /o/ recordings. Different parametric curves were fitted to the formant trajectories of the vowel tokens, and cross-validated likelihood ratios were calculated using a single-stage generative multivariate kernel density formula. The outputs of different systems were compared using C llr, a metric developed for automatic speaker recognition, and the cross-validated likelihood ratios were calibrated using a procedure developed for automatic speaker recognition. Calibration ameliorated some likelihood-ratio results which had offered strong support for a contrary-to-fact hypothesis.
KW - Calibration
KW - Forensic speaker recognition
KW - Formant trajectories
UR - http://www.scopus.com/inward/record.url?scp=84867191157&partnerID=8YFLogxK
UR - https://www.isca-speech.org/archive/interspeech_2008/i08_1501.html
M3 - Conference publication
AN - SCOPUS:84867191157
T3 - Proceedings of Interspeech
SP - 1501
EP - 1504
BT - Proceedings of the Annual Conference of the International Speech Communication Association
Y2 - 22 September 2008 through 26 September 2008
ER -