Home > Research > Publications & Outputs > Spoofed speech from the perspective of a forens...

Research

Associated organisational unit

Electronic data

  • CK_GB_spoof_interspeech_subv4

    Accepted author manuscript, 4.55 MB, PDF document

Links

Text available via DOI:

View graph of relations

Spoofed speech from the perspective of a forensic phonetician

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Published

Standard

Spoofed speech from the perspective of a forensic phonetician. / Kirchhuebel, Christin; Brown, Georgina.
2022. 1308-1312 Paper presented at Interspeech 2022, Incheon, Korea, Republic of.

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Harvard

Kirchhuebel, C & Brown, G 2022, 'Spoofed speech from the perspective of a forensic phonetician', Paper presented at Interspeech 2022, Incheon, Korea, Republic of, 8/09/22 - 22/09/22 pp. 1308-1312. https://doi.org/10.21437/Interspeech.2022-661

APA

Kirchhuebel, C., & Brown, G. (2022). Spoofed speech from the perspective of a forensic phonetician. 1308-1312. Paper presented at Interspeech 2022, Incheon, Korea, Republic of. https://doi.org/10.21437/Interspeech.2022-661

Vancouver

Kirchhuebel C, Brown G. Spoofed speech from the perspective of a forensic phonetician. 2022. Paper presented at Interspeech 2022, Incheon, Korea, Republic of. doi: 10.21437/Interspeech.2022-661

Author

Kirchhuebel, Christin ; Brown, Georgina. / Spoofed speech from the perspective of a forensic phonetician. Paper presented at Interspeech 2022, Incheon, Korea, Republic of.5 p.

Bibtex

@conference{e1003042807e4c79b734b7f19253ef9a,
title = "Spoofed speech from the perspective of a forensic phonetician",
abstract = "While previous work has uncovered the performances of automatic systems when presented with spoofed speech samples, this work looks deeper into these samples from the perspective of an experienced forensic phonetician. From an evaluation of 300 samples, this paper reveals how similar some of the spoofed speech samples are to genuine human speech samples. One speech synthesis method 'sticks out' in this respect by producing speech samples that bear a collection of natural speech characteristics. On the other hand, spoofing methods that have been shown to present problems to automatic systems in past work do not present problems to the forensic phonetician. The main contribution of this paper is a descriptive account of different spoofed speech samples, based on the auditory-acoustic evaluation of a forensic phonetician. This is to spark an awareness of the current possibilities of spoofing methods that perhaps have so far been 'off the radar' for many forensic phoneticians. Such an account can bring great value to the forensic phonetics community as spoofed speech samples could plausibly find their way into forensic casework scenarios.",
author = "Christin Kirchhuebel and Georgina Brown",
year = "2022",
month = sep,
day = "22",
doi = "10.21437/Interspeech.2022-661",
language = "English",
pages = "1308--1312",
note = "Interspeech 2022 ; Conference date: 08-09-2022 Through 22-09-2022",

}

RIS

TY - CONF

T1 - Spoofed speech from the perspective of a forensic phonetician

AU - Kirchhuebel, Christin

AU - Brown, Georgina

PY - 2022/9/22

Y1 - 2022/9/22

N2 - While previous work has uncovered the performances of automatic systems when presented with spoofed speech samples, this work looks deeper into these samples from the perspective of an experienced forensic phonetician. From an evaluation of 300 samples, this paper reveals how similar some of the spoofed speech samples are to genuine human speech samples. One speech synthesis method 'sticks out' in this respect by producing speech samples that bear a collection of natural speech characteristics. On the other hand, spoofing methods that have been shown to present problems to automatic systems in past work do not present problems to the forensic phonetician. The main contribution of this paper is a descriptive account of different spoofed speech samples, based on the auditory-acoustic evaluation of a forensic phonetician. This is to spark an awareness of the current possibilities of spoofing methods that perhaps have so far been 'off the radar' for many forensic phoneticians. Such an account can bring great value to the forensic phonetics community as spoofed speech samples could plausibly find their way into forensic casework scenarios.

AB - While previous work has uncovered the performances of automatic systems when presented with spoofed speech samples, this work looks deeper into these samples from the perspective of an experienced forensic phonetician. From an evaluation of 300 samples, this paper reveals how similar some of the spoofed speech samples are to genuine human speech samples. One speech synthesis method 'sticks out' in this respect by producing speech samples that bear a collection of natural speech characteristics. On the other hand, spoofing methods that have been shown to present problems to automatic systems in past work do not present problems to the forensic phonetician. The main contribution of this paper is a descriptive account of different spoofed speech samples, based on the auditory-acoustic evaluation of a forensic phonetician. This is to spark an awareness of the current possibilities of spoofing methods that perhaps have so far been 'off the radar' for many forensic phoneticians. Such an account can bring great value to the forensic phonetics community as spoofed speech samples could plausibly find their way into forensic casework scenarios.

U2 - 10.21437/Interspeech.2022-661

DO - 10.21437/Interspeech.2022-661

M3 - Conference paper

SP - 1308

EP - 1312

T2 - Interspeech 2022

Y2 - 8 September 2022 through 22 September 2022

ER -