Formant dynamics and durations of um improve the performance of automatic speaker recognition systems

Vincent Hughes; Paul Foulkes; Sophie Wood

Formant dynamics and durations of um improve the performance of automatic speaker recognition systems

Vincent Hughes, Paul Foulkes, Sophie Wood

Language and Linguistic Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We assess the potential improvement in the performance of MFCC-based automatic speaker recognition (ASR) systems with the inclusion of linguistic-phonetic information. Likelihood ratios were computed using MFCCs and the formant trajectories and durations of the hesitation marker um, extracted from recordings of male standard southern British English speakers. Testing was run over 20 replications using randomised sets of speakers. System validity (EER and Cllr) was found to improve with the inclusion of um relative to the baseline ASR across all 20 replications. These results offer support for the growing integration of automatic and linguistic-phonetic methods in forensic voice comparison.

Original language	English
Title of host publication	Proceedings of the 16th Australasian Conference on Speech Science and Technology (ASSTA)
Place of Publication	University of Western Sydney, Australia
Publication status	Published - 2016

Access to Document

Formant dynamics and durations of um improve the performance of automatic speaker recognition systems (Resubmission)Accepted author manuscript, 619 KB

Cite this

@inproceedings{35c5f9cc809a46a0b6336a617e50a7fe,

title = "Formant dynamics and durations of um improve the performance of automatic speaker recognition systems",

abstract = "We assess the potential improvement in the performance of MFCC-based automatic speaker recognition (ASR) systems with the inclusion of linguistic-phonetic information. Likelihood ratios were computed using MFCCs and the formant trajectories and durations of the hesitation marker um, extracted from recordings of male standard southern British English speakers. Testing was run over 20 replications using randomised sets of speakers. System validity (EER and Cllr) was found to improve with the inclusion of um relative to the baseline ASR across all 20 replications. These results offer support for the growing integration of automatic and linguistic-phonetic methods in forensic voice comparison.",

author = "Vincent Hughes and Paul Foulkes and Sophie Wood",

year = "2016",

language = "English",

booktitle = "Proceedings of the 16th Australasian Conference on Speech Science and Technology (ASSTA)",

}

Formant dynamics and durations of um improve the performance of automatic speaker recognition systems. / Hughes, Vincent ; Foulkes, Paul; Wood, Sophie.
Proceedings of the 16th Australasian Conference on Speech Science and Technology (ASSTA). University of Western Sydney, Australia, 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Formant dynamics and durations of um improve the performance of automatic speaker recognition systems

AU - Hughes, Vincent

AU - Foulkes, Paul

AU - Wood, Sophie

PY - 2016

Y1 - 2016

N2 - We assess the potential improvement in the performance of MFCC-based automatic speaker recognition (ASR) systems with the inclusion of linguistic-phonetic information. Likelihood ratios were computed using MFCCs and the formant trajectories and durations of the hesitation marker um, extracted from recordings of male standard southern British English speakers. Testing was run over 20 replications using randomised sets of speakers. System validity (EER and Cllr) was found to improve with the inclusion of um relative to the baseline ASR across all 20 replications. These results offer support for the growing integration of automatic and linguistic-phonetic methods in forensic voice comparison.

AB - We assess the potential improvement in the performance of MFCC-based automatic speaker recognition (ASR) systems with the inclusion of linguistic-phonetic information. Likelihood ratios were computed using MFCCs and the formant trajectories and durations of the hesitation marker um, extracted from recordings of male standard southern British English speakers. Testing was run over 20 replications using randomised sets of speakers. System validity (EER and Cllr) was found to improve with the inclusion of um relative to the baseline ASR across all 20 replications. These results offer support for the growing integration of automatic and linguistic-phonetic methods in forensic voice comparison.

M3 - Conference contribution

BT - Proceedings of the 16th Australasian Conference on Speech Science and Technology (ASSTA)

CY - University of Western Sydney, Australia

ER -