Simulating spontaneous speech: application to forensic voice comparison

Yuko Kinoshita; Michael Norris

Simulating spontaneous speech: application to forensic voice comparison

Yuko Kinoshita, Michael Norris

Arts & Communication

Research output: A Conference proceeding or a Chapter in Book › Conference contribution

Abstract

We investigated the feasibility of improving the reliability of LR calculations by creating a simulated background population. Using spontaneous speech and carefully read-out speech from 18 male speakers of Australian English in the ANDOSL database, we modelled the characteristics of the two speech styles and applied the model to Bernard’s formant data to simulate spontaneous speech data from it. We calculated two sets of LRs using two different background populations: Bernard’s original data, and the simulated spontaneous speech data. The simulated spontaneous speech data did not perform better in the classification of speaker pairs, but did improve the calibration of the LRs significantly.

Original language	English
Title of host publication	Proceedings of the 13th Australasian International Conference on Speech Science and Technology
Place of Publication	Melbourne, Australia
Publisher	Australian Speech Science and Technology Association (ASSTA)
Pages	26-29
Number of pages	4
ISBN (Print)	9780958194631
Publication status	Published - 2010
Event	SST 2010: Thirteenth Australasian International Conference on Speech Science and Technology 2010 - Melbourne, Australia Duration: 14 Dec 2010 → 16 Dec 2010

Conference

Conference	SST 2010: Thirteenth Australasian International Conference on Speech Science and Technology 2010
Country/Territory	Australia
City	Melbourne
Period	14/12/10 → 16/12/10

Access to Document

http://assta.org/sst/SST-10/SST2010/PDF/AUTHOR/ST100035.PDF

Cite this

@inproceedings{c15eb28117af4238a35b5e1d0b7a37e7,

title = "Simulating spontaneous speech: application to forensic voice comparison",

abstract = "We investigated the feasibility of improving the reliability of LR calculations by creating a simulated background population. Using spontaneous speech and carefully read-out speech from 18 male speakers of Australian English in the ANDOSL database, we modelled the characteristics of the two speech styles and applied the model to Bernard{\textquoteright}s formant data to simulate spontaneous speech data from it. We calculated two sets of LRs using two different background populations: Bernard{\textquoteright}s original data, and the simulated spontaneous speech data. The simulated spontaneous speech data did not perform better in the classification of speaker pairs, but did improve the calibration of the LRs significantly.",

author = "Yuko Kinoshita and Michael Norris",

year = "2010",

language = "English",

isbn = "9780958194631",

pages = "26--29",

booktitle = "Proceedings of the 13th Australasian International Conference on Speech Science and Technology",

publisher = "Australian Speech Science and Technology Association (ASSTA)",

note = "SST 2010: Thirteenth Australasian International Conference on Speech Science and Technology 2010 ; Conference date: 14-12-2010 Through 16-12-2010",

}

Kinoshita, Y & Norris, M 2010, Simulating spontaneous speech: application to forensic voice comparison. in Proceedings of the 13th Australasian International Conference on Speech Science and Technology. Australian Speech Science and Technology Association (ASSTA), Melbourne, Australia, pp. 26-29, SST 2010: Thirteenth Australasian International Conference on Speech Science and Technology 2010, Melbourne, Australia, 14/12/10. <http://assta.org/sst/SST-10/SST2010/PDF/AUTHOR/ST100035.PDF>

Simulating spontaneous speech: application to forensic voice comparison. / Kinoshita, Yuko; Norris, Michael.
Proceedings of the 13th Australasian International Conference on Speech Science and Technology. Melbourne, Australia: Australian Speech Science and Technology Association (ASSTA), 2010. p. 26-29.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution

TY - GEN

T1 - Simulating spontaneous speech: application to forensic voice comparison

AU - Kinoshita, Yuko

AU - Norris, Michael

PY - 2010

Y1 - 2010

N2 - We investigated the feasibility of improving the reliability of LR calculations by creating a simulated background population. Using spontaneous speech and carefully read-out speech from 18 male speakers of Australian English in the ANDOSL database, we modelled the characteristics of the two speech styles and applied the model to Bernard’s formant data to simulate spontaneous speech data from it. We calculated two sets of LRs using two different background populations: Bernard’s original data, and the simulated spontaneous speech data. The simulated spontaneous speech data did not perform better in the classification of speaker pairs, but did improve the calibration of the LRs significantly.

AB - We investigated the feasibility of improving the reliability of LR calculations by creating a simulated background population. Using spontaneous speech and carefully read-out speech from 18 male speakers of Australian English in the ANDOSL database, we modelled the characteristics of the two speech styles and applied the model to Bernard’s formant data to simulate spontaneous speech data from it. We calculated two sets of LRs using two different background populations: Bernard’s original data, and the simulated spontaneous speech data. The simulated spontaneous speech data did not perform better in the classification of speaker pairs, but did improve the calibration of the LRs significantly.

M3 - Conference contribution

SN - 9780958194631

SP - 26

EP - 29

BT - Proceedings of the 13th Australasian International Conference on Speech Science and Technology

PB - Australian Speech Science and Technology Association (ASSTA)

CY - Melbourne, Australia

T2 - SST 2010: Thirteenth Australasian International Conference on Speech Science and Technology 2010

Y2 - 14 December 2010 through 16 December 2010

ER -