How many do we need? Exploration of the population size effect on the performance of forensic speaker classification

Shunichi Ishihara; Yuko Kinoshita

How many do we need? Exploration of the population size effect on the performance of forensic speaker classification

Shunichi Ishihara^*, Yuko Kinoshita

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

18 Citations (Scopus)

Abstract

This paper investigates how change in population size affects the reliability of the likelihood ratio (LR)-based forensic speaker classification. Using features of the long term F0 distribution, we performed LR-based speaker classification and examined its performance with population sizes from 10 to 120. The results revealed that LRs could be heavily influenced by the population data. We discovered that the reliability of LR-based evaluation of the evidence was heavily compromised if the population data was limited to a small number of speakers.

Original language	English
Pages (from-to)	1941-1944
Number of pages	4
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication status	Published - 2008
Event	INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association - Brisbane, QLD, Australia Duration: 22 Sept 2008 → 26 Sept 2008

Cite this

@article{8d7c412ec9cf4e6a923a31bf524f464f,

title = "How many do we need? Exploration of the population size effect on the performance of forensic speaker classification",

abstract = "This paper investigates how change in population size affects the reliability of the likelihood ratio (LR)-based forensic speaker classification. Using features of the long term F0 distribution, we performed LR-based speaker classification and examined its performance with population sizes from 10 to 120. The results revealed that LRs could be heavily influenced by the population data. We discovered that the reliability of LR-based evaluation of the evidence was heavily compromised if the population data was limited to a small number of speakers.",

keywords = "Forensic, Japanese, Likelihood ratio, Long term F0 distribution, MVLR, Population, Speaker classification, Spontaneous speech",

author = "Shunichi Ishihara and Yuko Kinoshita",

year = "2008",

language = "English",

pages = "1941--1944",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

note = "INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association ; Conference date: 22-09-2008 Through 26-09-2008",

}

TY - JOUR

T1 - How many do we need? Exploration of the population size effect on the performance of forensic speaker classification

AU - Ishihara, Shunichi

AU - Kinoshita, Yuko

PY - 2008

Y1 - 2008

N2 - This paper investigates how change in population size affects the reliability of the likelihood ratio (LR)-based forensic speaker classification. Using features of the long term F0 distribution, we performed LR-based speaker classification and examined its performance with population sizes from 10 to 120. The results revealed that LRs could be heavily influenced by the population data. We discovered that the reliability of LR-based evaluation of the evidence was heavily compromised if the population data was limited to a small number of speakers.

AB - This paper investigates how change in population size affects the reliability of the likelihood ratio (LR)-based forensic speaker classification. Using features of the long term F0 distribution, we performed LR-based speaker classification and examined its performance with population sizes from 10 to 120. The results revealed that LRs could be heavily influenced by the population data. We discovered that the reliability of LR-based evaluation of the evidence was heavily compromised if the population data was limited to a small number of speakers.

KW - Forensic

KW - Japanese

KW - Likelihood ratio

KW - Long term F0 distribution

KW - MVLR

KW - Population

KW - Speaker classification

KW - Spontaneous speech

UR - http://www.scopus.com/inward/record.url?scp=84867193857&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84867193857

SN - 2308-457X

SP - 1941

EP - 1944

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association

Y2 - 22 September 2008 through 26 September 2008

ER -

How many do we need? Exploration of the population size effect on the performance of forensic speaker classification

Abstract

Other files and links

Fingerprint

Cite this