On the enhancement of speaker identification accuracy using weighted bilateral scoring

A. Malegaonkar; A. Ariyaeeinia; P. Sivakumaran; J. Fortuna

doi:10.1109/CCST.2008.4751310

On the enhancement of speaker identification accuracy using weighted bilateral scoring

A. Malegaonkar, A. Ariyaeeinia, P. Sivakumaran, J. Fortuna

Research output: Contribution to conference › Paper › peer-review

9 Citations (Scopus)

37 Downloads (Pure)

Abstract

This paper presents investigations into an effective bilateral scoring method in open-set speaker identification. The approach is based on the fact that two different speakers usually are not reciprocal. A difficulty in deploying bilateral scoring is that test utterances are normally much shorter than training utterances. To tackle this problem, the proposed approach provides the final identification score based on a weighted combination of independently normalised forward and reverse scores. Based on the experimental results obtained using clean and telephone quality speech, it is shown that the proposed approach is more effective than the conventional scoring methods in open-set speaker identification.

Original language	English
Pages	254-258
DOIs	https://doi.org/10.1109/CCST.2008.4751310
Publication status	Published - 16 Oct 2008
Event	42nd Annual IEEE International Carnahan Conference on Security Technology - Prague, Czech Republic Duration: 13 Oct 2008 → 16 Oct 2008 Conference number: 42nd

Conference

Conference	42nd Annual IEEE International Carnahan Conference on Security Technology
Country/Territory	Czech Republic
City	Prague
Period	13/10/08 → 16/10/08

Access to Document

10.1109/CCST.2008.4751310

04751310Final published version, 567 KB

Cite this

@conference{d2e8bb50429d4625877d306c5d0baf92,

title = "On the enhancement of speaker identification accuracy using weighted bilateral scoring",

abstract = "This paper presents investigations into an effective bilateral scoring method in open-set speaker identification. The approach is based on the fact that two different speakers usually are not reciprocal. A difficulty in deploying bilateral scoring is that test utterances are normally much shorter than training utterances. To tackle this problem, the proposed approach provides the final identification score based on a weighted combination of independently normalised forward and reverse scores. Based on the experimental results obtained using clean and telephone quality speech, it is shown that the proposed approach is more effective than the conventional scoring methods in open-set speaker identification.",

author = "A. Malegaonkar and A. Ariyaeeinia and P. Sivakumaran and J. Fortuna",

note = "“This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.{"} “Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.” DOI: 10.1109/CCST.2008.4751310; 42nd Annual IEEE International Carnahan Conference on Security Technology ; Conference date: 13-10-2008 Through 16-10-2008",

year = "2008",

month = oct,

day = "16",

doi = "10.1109/CCST.2008.4751310",

language = "English",

pages = "254--258",

}

TY - CONF

T1 - On the enhancement of speaker identification accuracy using weighted bilateral scoring

AU - Malegaonkar, A.

AU - Ariyaeeinia, A.

AU - Sivakumaran, P.

AU - Fortuna, J.

N1 - Conference code: 42nd

PY - 2008/10/16

Y1 - 2008/10/16

N2 - This paper presents investigations into an effective bilateral scoring method in open-set speaker identification. The approach is based on the fact that two different speakers usually are not reciprocal. A difficulty in deploying bilateral scoring is that test utterances are normally much shorter than training utterances. To tackle this problem, the proposed approach provides the final identification score based on a weighted combination of independently normalised forward and reverse scores. Based on the experimental results obtained using clean and telephone quality speech, it is shown that the proposed approach is more effective than the conventional scoring methods in open-set speaker identification.

AB - This paper presents investigations into an effective bilateral scoring method in open-set speaker identification. The approach is based on the fact that two different speakers usually are not reciprocal. A difficulty in deploying bilateral scoring is that test utterances are normally much shorter than training utterances. To tackle this problem, the proposed approach provides the final identification score based on a weighted combination of independently normalised forward and reverse scores. Based on the experimental results obtained using clean and telephone quality speech, it is shown that the proposed approach is more effective than the conventional scoring methods in open-set speaker identification.

U2 - 10.1109/CCST.2008.4751310

DO - 10.1109/CCST.2008.4751310

M3 - Paper

SP - 254

EP - 258

T2 - 42nd Annual IEEE International Carnahan Conference on Security Technology

Y2 - 13 October 2008 through 16 October 2008

ER -

On the enhancement of speaker identification accuracy using weighted bilateral scoring

Abstract

Conference

Access to Document

Fingerprint

Cite this