Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals

Rahim Saeidi; Pejman Mowlaee; Tomi  Kinnunen; Zheng-Hua Tan; Mads Græsbøll Christensen; Søren Holdt Jensen; Pasi  Fränti

doi:10.1109/ICPR.2010.1131

Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals

Rahim Saeidi, Pejman Mowlaee, Tomi Kinnunen, Zheng-Hua Tan, Mads Græsbøll Christensen, Søren Holdt Jensen, Pasi Fränti

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

19 Citations (Scopus)

562 Downloads (Pure)

Abstract

In this paper, we consider speaker identification
for the co-channel scenario in which speech mixture from
speakers is recorded by one microphone only. The goal is to
identify both of the speakers from their mixed signal. High
recognition accuracies have already been reported when an
accurately estimated signal-to-signal ratio (SSR) is available. In
this paper, we approach the problem without estimating SSR.
We show that a simple method based on fusion of adapted
Gaussian mixture models and Kullback-Leibler divergence
calculated between models, achieves an accuracy of 97% and
93% when the two target speakers enlisted as three and two
most probable speakers, respectively.

Original language	English
Title of host publication	IEEE International Conference on Pattern Recognition (ICPR 2010) : Proceedings
Publisher	IEEE Press
Publication date	2010
Pages	4565-4568
ISBN (Electronic)	978-0-7695-4109-9
DOIs	https://doi.org/10.1109/ICPR.2010.1131
Publication status	Published - 2010
Event	20 th International Conference on Pattern Recognition (ICPR) - Istanbul, Turkey Duration: 23 Aug 2010 → 26 Aug 2010

Conference

Conference	20 th International Conference on Pattern Recognition (ICPR)
Country/Territory	Turkey
City	Istanbul
Period	23/08/2010 → 26/08/2010

Series	Proceeding IEEE International Conference on Pattern Recognition (ICPR)
ISSN	1051-4651

Access to Document

10.1109/ICPR.2010.1131

Icpr2010Accepted author manuscript, 828 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{fd9ead9b17cf4c978918ae372f5d5afa,

title = "Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals",

abstract = "In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture fromspeakers is recorded by one microphone only. The goal is toidentify both of the speakers from their mixed signal. Highrecognition accuracies have already been reported when anaccurately estimated signal-to-signal ratio (SSR) is available. Inthis paper, we approach the problem without estimating SSR.We show that a simple method based on fusion of adaptedGaussian mixture models and Kullback-Leibler divergencecalculated between models, achieves an accuracy of 97% and93% when the two target speakers enlisted as three and twomost probable speakers, respectively.",

author = "Rahim Saeidi and Pejman Mowlaee and Tomi Kinnunen and Zheng-Hua Tan and Christensen, {Mads Gr{\ae}sb{\o}ll} and Jensen, {S{\o}ren Holdt} and Pasi Fr{\"a}nti",

year = "2010",

doi = "10.1109/ICPR.2010.1131",

language = "English",

series = "Proceeding IEEE International Conference on Pattern Recognition (ICPR)",

publisher = "IEEE Press",

pages = "4565--4568",

booktitle = "IEEE International Conference on Pattern Recognition (ICPR 2010)",

note = "20 th International Conference on Pattern Recognition (ICPR) ; Conference date: 23-08-2010 Through 26-08-2010",

}

Saeidi, R, Mowlaee, P, Kinnunen, T, Tan, Z-H , Christensen, MG, Jensen, SH & Fränti, P 2010, Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals. in IEEE International Conference on Pattern Recognition (ICPR 2010): Proceedings. IEEE Press, Proceeding IEEE International Conference on Pattern Recognition (ICPR), pp. 4565-4568, 20 th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 23/08/2010. https://doi.org/10.1109/ICPR.2010.1131

Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals. / Saeidi, Rahim; Mowlaee, Pejman; Kinnunen, Tomi et al.
IEEE International Conference on Pattern Recognition (ICPR 2010): Proceedings. IEEE Press, 2010. p. 4565-4568 (Proceeding IEEE International Conference on Pattern Recognition (ICPR)).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals

AU - Saeidi, Rahim

AU - Mowlaee, Pejman

AU - Kinnunen, Tomi

AU - Tan, Zheng-Hua

AU - Christensen, Mads Græsbøll

AU - Jensen, Søren Holdt

AU - Fränti, Pasi

PY - 2010

Y1 - 2010

N2 - In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture fromspeakers is recorded by one microphone only. The goal is toidentify both of the speakers from their mixed signal. Highrecognition accuracies have already been reported when anaccurately estimated signal-to-signal ratio (SSR) is available. Inthis paper, we approach the problem without estimating SSR.We show that a simple method based on fusion of adaptedGaussian mixture models and Kullback-Leibler divergencecalculated between models, achieves an accuracy of 97% and93% when the two target speakers enlisted as three and twomost probable speakers, respectively.

AB - In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture fromspeakers is recorded by one microphone only. The goal is toidentify both of the speakers from their mixed signal. Highrecognition accuracies have already been reported when anaccurately estimated signal-to-signal ratio (SSR) is available. Inthis paper, we approach the problem without estimating SSR.We show that a simple method based on fusion of adaptedGaussian mixture models and Kullback-Leibler divergencecalculated between models, achieves an accuracy of 97% and93% when the two target speakers enlisted as three and twomost probable speakers, respectively.

U2 - 10.1109/ICPR.2010.1131

DO - 10.1109/ICPR.2010.1131

M3 - Article in proceeding

T3 - Proceeding IEEE International Conference on Pattern Recognition (ICPR)

SP - 4565

EP - 4568

BT - IEEE International Conference on Pattern Recognition (ICPR 2010)

PB - IEEE Press

T2 - 20 th International Conference on Pattern Recognition (ICPR)

Y2 - 23 August 2010 through 26 August 2010

ER -

Saeidi R, Mowlaee P, Kinnunen T, Tan Z-H , Christensen MG, Jensen SH et al. Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals. In IEEE International Conference on Pattern Recognition (ICPR 2010): Proceedings. IEEE Press. 2010. p. 4565-4568. (Proceeding IEEE International Conference on Pattern Recognition (ICPR)). doi: 10.1109/ICPR.2010.1131

Signal-to-Signal Ratio Independent Speaker Identification for Co-channel Speech Signals

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Cite this