Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age

Girija Chetty; Michael Wagner

Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age

Girija Chetty, Michael Wagner

Information Systems

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

39 Downloads (Pure)

Abstract

Multimodal speaker verification based on easy-to-obtain biometric traits such as face and voice is rapidly gaining acceptance as the preferred technology for many applications. In many such practical applications, other characteristics of the speaker such as gender or age are known and may be exploited for enhanced verification accuracy. In this paper we present a parallel approach determining gender as an ancillary speaker characteristic, which is incorporated in the decision of a face-voice speaker verification system. Preliminary experiments with the DaFEx multimodal audio-video database show that fusing the results of gender recognition and identity verification improves the performance of multimodal speaker verification.

Original language	English
Title of host publication	10th Annual Conference of the International Speech Communication Association (Interspeech 2009)
Editors	M Uther
Place of Publication	Brighton, UK
Publisher	International Speech Communication Association
Pages	1167-1170
Number of pages	4
ISBN (Print)	9781615676927
Publication status	Published - 2009
Event	Interspeech-2009 - Brighton, United Kingdom Duration: 6 Sept 2009 → 9 Sept 2009

Conference

Conference	Interspeech-2009
Country/Territory	United Kingdom
City	Brighton
Period	6/09/09 → 9/09/09

Access to Document

PaperFinal published version, 264 KB

Cite this

@inproceedings{e8a742d0aaa84fbe885f520c43890bd6,

title = "Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age",

abstract = "Multimodal speaker verification based on easy-to-obtain biometric traits such as face and voice is rapidly gaining acceptance as the preferred technology for many applications. In many such practical applications, other characteristics of the speaker such as gender or age are known and may be exploited for enhanced verification accuracy. In this paper we present a parallel approach determining gender as an ancillary speaker characteristic, which is incorporated in the decision of a face-voice speaker verification system. Preliminary experiments with the DaFEx multimodal audio-video database show that fusing the results of gender recognition and identity verification improves the performance of multimodal speaker verification. ",

author = "Girija Chetty and Michael Wagner",

year = "2009",

language = "English",

isbn = "9781615676927",

pages = "1167--1170",

editor = "M Uther",

booktitle = "10th Annual Conference of the International Speech Communication Association (Interspeech 2009)",

publisher = "International Speech Communication Association",

note = "Interspeech-2009 ; Conference date: 06-09-2009 Through 09-09-2009",

}

Chetty, G & Wagner, M 2009, Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age. in M Uther (ed.), 10th Annual Conference of the International Speech Communication Association (Interspeech 2009). International Speech Communication Association, Brighton, UK, pp. 1167-1170, Interspeech-2009, Brighton, United Kingdom, 6/09/09.

Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age. / Chetty, Girija; Wagner, Michael.
10th Annual Conference of the International Speech Communication Association (Interspeech 2009). ed. / M Uther. Brighton, UK: International Speech Communication Association, 2009. p. 1167-1170.

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

TY - GEN

T1 - Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age

AU - Chetty, Girija

AU - Wagner, Michael

PY - 2009

Y1 - 2009

N2 - Multimodal speaker verification based on easy-to-obtain biometric traits such as face and voice is rapidly gaining acceptance as the preferred technology for many applications. In many such practical applications, other characteristics of the speaker such as gender or age are known and may be exploited for enhanced verification accuracy. In this paper we present a parallel approach determining gender as an ancillary speaker characteristic, which is incorporated in the decision of a face-voice speaker verification system. Preliminary experiments with the DaFEx multimodal audio-video database show that fusing the results of gender recognition and identity verification improves the performance of multimodal speaker verification.

AB - Multimodal speaker verification based on easy-to-obtain biometric traits such as face and voice is rapidly gaining acceptance as the preferred technology for many applications. In many such practical applications, other characteristics of the speaker such as gender or age are known and may be exploited for enhanced verification accuracy. In this paper we present a parallel approach determining gender as an ancillary speaker characteristic, which is incorporated in the decision of a face-voice speaker verification system. Preliminary experiments with the DaFEx multimodal audio-video database show that fusing the results of gender recognition and identity verification improves the performance of multimodal speaker verification.

M3 - Conference contribution

SN - 9781615676927

SP - 1167

EP - 1170

BT - 10th Annual Conference of the International Speech Communication Association (Interspeech 2009)

A2 - Uther, M

PB - International Speech Communication Association

CY - Brighton, UK

T2 - Interspeech-2009

Y2 - 6 September 2009 through 9 September 2009

ER -

Multimodal Speaker Verification Using Ancillary Known Speaker Characteristics Such as Gender or Age

Abstract

Conference

Access to Document

Fingerprint

Cite this