The individual and the system: Assessing the stability of the output of a semi-automatic forensic voice comparison system

Vincent Hughes; Philip Thomas Harrison; Paul Foulkes; John Peter French; Colleen Kavanagh; Eugenia San Segundo Fernandez

The individual and the system: Assessing the stability of the output of a semi-automatic forensic voice comparison system

Vincent Hughes, Philip Thomas Harrison, Paul Foulkes, John Peter French, Colleen Kavanagh, Eugenia San Segundo Fernandez

Language and Linguistic Science

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

Abstract

Semi-automatic systems based on traditional linguistic-phonetic features are increasingly being used for forensic voice comparison (FVC) casework. In this paper, we examine the stability of the output of a semi-automatic system, based on the long-term formant distributions (LTFDs) of F1, F2, and F3, as the channel quality of the input recordings decreases. Cross-validated, calibrated GMM-UBM log likelihood-ratios (LLRs) were computed for 97 Standard Southern British English speakers under four conditions. In each condition the same speech material was used, but the technical properties of the recordings changed (high quality studio recording, landline telephone recording, high bit-rate GSM mobile telephone recording and low bit-rate GSM mobile telephone recording). Equal error rate (EER) and the log LR cost function (Cllr) were compared across conditions. System validity was found to decrease with poorer technical quality, with the largest differences in EER (21.66%) and Cllr (0.46) found between the studio and the low bit-rate GSM conditions. However, importantly, performance for individual speakers was affected differently by channel quality. Speakers that produced stronger evidence overall were found to be more variable. Mean F3 was also found to be a predictor of LLR variability, however no effects were found based on speakers’ voice quality profiles.

Original language	English
Title of host publication	Proceedings of Interspeech 2018
Publication status	Published - 2018

Bibliographical note

This is an author-produced version of the published paper. Uploaded with permission of the publisher/copyright holder. Further copying may not be permitted; contact the publisher for details

Access to Document

Hughes et al - Interspeech 2018
This is an author-produced version of the published paper. Uploaded with permission of the publisher/copyright holder. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 544 KB

Cite this

@inproceedings{c8001b5fca0a41d0b7ffea40288d89ac,

title = "The individual and the system: Assessing the stability of the output of a semi-automatic forensic voice comparison system",

abstract = "Semi-automatic systems based on traditional linguistic-phonetic features are increasingly being used for forensic voice comparison (FVC) casework. In this paper, we examine the stability of the output of a semi-automatic system, based on the long-term formant distributions (LTFDs) of F1, F2, and F3, as the channel quality of the input recordings decreases. Cross-validated, calibrated GMM-UBM log likelihood-ratios (LLRs) were computed for 97 Standard Southern British English speakers under four conditions. In each condition the same speech material was used, but the technical properties of the recordings changed (high quality studio recording, landline telephone recording, high bit-rate GSM mobile telephone recording and low bit-rate GSM mobile telephone recording). Equal error rate (EER) and the log LR cost function (Cllr) were compared across conditions. System validity was found to decrease with poorer technical quality, with the largest differences in EER (21.66%) and Cllr (0.46) found between the studio and the low bit-rate GSM conditions. However, importantly, performance for individual speakers was affected differently by channel quality. Speakers that produced stronger evidence overall were found to be more variable. Mean F3 was also found to be a predictor of LLR variability, however no effects were found based on speakers{\textquoteright} voice quality profiles.",

author = "Vincent Hughes and Harrison, {Philip Thomas} and Paul Foulkes and French, {John Peter} and Colleen Kavanagh and {San Segundo Fernandez}, Eugenia",

note = "This is an author-produced version of the published paper. Uploaded with permission of the publisher/copyright holder. Further copying may not be permitted; contact the publisher for details",

year = "2018",

language = "English",

booktitle = "Proceedings of Interspeech 2018",

}

TY - GEN

T1 - The individual and the system

T2 - Assessing the stability of the output of a semi-automatic forensic voice comparison system

AU - Hughes, Vincent

AU - Harrison, Philip Thomas

AU - Foulkes, Paul

AU - French, John Peter

AU - Kavanagh, Colleen

AU - San Segundo Fernandez, Eugenia

N1 - This is an author-produced version of the published paper. Uploaded with permission of the publisher/copyright holder. Further copying may not be permitted; contact the publisher for details

PY - 2018

Y1 - 2018

N2 - Semi-automatic systems based on traditional linguistic-phonetic features are increasingly being used for forensic voice comparison (FVC) casework. In this paper, we examine the stability of the output of a semi-automatic system, based on the long-term formant distributions (LTFDs) of F1, F2, and F3, as the channel quality of the input recordings decreases. Cross-validated, calibrated GMM-UBM log likelihood-ratios (LLRs) were computed for 97 Standard Southern British English speakers under four conditions. In each condition the same speech material was used, but the technical properties of the recordings changed (high quality studio recording, landline telephone recording, high bit-rate GSM mobile telephone recording and low bit-rate GSM mobile telephone recording). Equal error rate (EER) and the log LR cost function (Cllr) were compared across conditions. System validity was found to decrease with poorer technical quality, with the largest differences in EER (21.66%) and Cllr (0.46) found between the studio and the low bit-rate GSM conditions. However, importantly, performance for individual speakers was affected differently by channel quality. Speakers that produced stronger evidence overall were found to be more variable. Mean F3 was also found to be a predictor of LLR variability, however no effects were found based on speakers’ voice quality profiles.

AB - Semi-automatic systems based on traditional linguistic-phonetic features are increasingly being used for forensic voice comparison (FVC) casework. In this paper, we examine the stability of the output of a semi-automatic system, based on the long-term formant distributions (LTFDs) of F1, F2, and F3, as the channel quality of the input recordings decreases. Cross-validated, calibrated GMM-UBM log likelihood-ratios (LLRs) were computed for 97 Standard Southern British English speakers under four conditions. In each condition the same speech material was used, but the technical properties of the recordings changed (high quality studio recording, landline telephone recording, high bit-rate GSM mobile telephone recording and low bit-rate GSM mobile telephone recording). Equal error rate (EER) and the log LR cost function (Cllr) were compared across conditions. System validity was found to decrease with poorer technical quality, with the largest differences in EER (21.66%) and Cllr (0.46) found between the studio and the low bit-rate GSM conditions. However, importantly, performance for individual speakers was affected differently by channel quality. Speakers that produced stronger evidence overall were found to be more variable. Mean F3 was also found to be a predictor of LLR variability, however no effects were found based on speakers’ voice quality profiles.

M3 - Conference contribution

BT - Proceedings of Interspeech 2018

ER -