Reliability of human-supervised formant-trajectory measurement for forensic voice comparison

Cuiling Zhang, Geoffrey Stewart Morrison, Felipe Ochoa, Ewald Enzinger

Research output: Contribution to journalArticle

Abstract

Acoustic-phonetic approaches to forensic voice comparison often include human-supervised measurement of vowel formants, but the reliability of such measurements is a matter of concern. This study assesses the within- and between-supervisor variability of three sets of formant-trajectory measurements made by each of four human supervisors. It also assesses the validity and reliability of forensic-voice-comparison systems based on these measurements. Each supervisor's formant-trajectory system was fused with a baseline mel-frequency cepstral-coefficient system, and performance was assessed relative to the baseline system. Substantial improvements in validity were found for all supervisors' systems, but some supervisors' systems were more reliable than others.

Original languageEnglish
Article numberEL54
JournalJournal of the Acoustical Society of America
Volume133
Issue number1
DOIs
Publication statusPublished - Jan 2013

Fingerprint

trajectory measurement
phonetics
vowels
trajectories
acoustics
coefficients
Formants
Trajectory
Supervisors

Cite this

@article{05ced5728e134f2fbb2354293837ff36,
title = "Reliability of human-supervised formant-trajectory measurement for forensic voice comparison",
abstract = "Acoustic-phonetic approaches to forensic voice comparison often include human-supervised measurement of vowel formants, but the reliability of such measurements is a matter of concern. This study assesses the within- and between-supervisor variability of three sets of formant-trajectory measurements made by each of four human supervisors. It also assesses the validity and reliability of forensic-voice-comparison systems based on these measurements. Each supervisor's formant-trajectory system was fused with a baseline mel-frequency cepstral-coefficient system, and performance was assessed relative to the baseline system. Substantial improvements in validity were found for all supervisors' systems, but some supervisors' systems were more reliable than others.",
author = "Cuiling Zhang and Morrison, {Geoffrey Stewart} and Felipe Ochoa and Ewald Enzinger",
year = "2013",
month = "1",
doi = "10.1121/1.4773223",
language = "English",
volume = "133",
journal = "Journal of the Acoustical Society of America",
issn = "0001-4966",
publisher = "Acoustical Society of America",
number = "1",

}

Reliability of human-supervised formant-trajectory measurement for forensic voice comparison. / Zhang, Cuiling; Morrison, Geoffrey Stewart; Ochoa, Felipe; Enzinger, Ewald.

In: Journal of the Acoustical Society of America, Vol. 133, No. 1, EL54, 01.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Reliability of human-supervised formant-trajectory measurement for forensic voice comparison

AU - Zhang, Cuiling

AU - Morrison, Geoffrey Stewart

AU - Ochoa, Felipe

AU - Enzinger, Ewald

PY - 2013/1

Y1 - 2013/1

N2 - Acoustic-phonetic approaches to forensic voice comparison often include human-supervised measurement of vowel formants, but the reliability of such measurements is a matter of concern. This study assesses the within- and between-supervisor variability of three sets of formant-trajectory measurements made by each of four human supervisors. It also assesses the validity and reliability of forensic-voice-comparison systems based on these measurements. Each supervisor's formant-trajectory system was fused with a baseline mel-frequency cepstral-coefficient system, and performance was assessed relative to the baseline system. Substantial improvements in validity were found for all supervisors' systems, but some supervisors' systems were more reliable than others.

AB - Acoustic-phonetic approaches to forensic voice comparison often include human-supervised measurement of vowel formants, but the reliability of such measurements is a matter of concern. This study assesses the within- and between-supervisor variability of three sets of formant-trajectory measurements made by each of four human supervisors. It also assesses the validity and reliability of forensic-voice-comparison systems based on these measurements. Each supervisor's formant-trajectory system was fused with a baseline mel-frequency cepstral-coefficient system, and performance was assessed relative to the baseline system. Substantial improvements in validity were found for all supervisors' systems, but some supervisors' systems were more reliable than others.

UR - http://www.scopus.com/inward/record.url?scp=84872073195&partnerID=8YFLogxK

UR - https://asa.scitation.org/doi/full/10.1121/1.4773223

U2 - 10.1121/1.4773223

DO - 10.1121/1.4773223

M3 - Article

VL - 133

JO - Journal of the Acoustical Society of America

JF - Journal of the Acoustical Society of America

SN - 0001-4966

IS - 1

M1 - EL54

ER -