Open-set speaker identification in broadcast news

Author

Gao, Chao ; Saikumar, Guruprasad ; Srivastava, Amit ; Natarajan, Premkumar

Author_Institution

Raytheon BBN Technol., Cambridge, MA, USA

fYear

2011

fDate

22-27 May 2011

Firstpage

5280

Lastpage

5283

Abstract

In this paper, we examine the problem of text-independent open-set speaker identification (OS-SI) in broadcast news. Particularly, the impact of the population of registered speakers to OS-SI performance is investigated, which is the central issue for designing practical OS-SI system. We amend the maximum mutual information (MMI)-based discriminative training scheme to facilitate its incorporation in OS-SI systems. We also improve the implementation to allow the application of MMI based approach with 2048-component Gaussian mixture models. All systems are evaluated using NIST RT-03, RT-04 and FBIS corpora, with a maximum of 82 registered speakers. Our study shows that notable performance improvement can be obtained with MMI-based discriminative training, which reduces the equal error rate (EER) by 15.9% relatively, in comparison to the GMM-MAP scheme.

Keywords

Gaussian processes; speaker recognition; 2048-component Gaussian mixture models; EER; GMM-MAP scheme; MMI-based discriminative training; OS-SI system; broadcast news; equal error rate; open-set speaker identification; Adaptation models; Computational modeling; Monitoring; Speaker recognition; System performance; Training; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on

Conference_Location

Prague

ISSN

1520-6149

Print_ISBN

978-1-4577-0538-0

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2011.5947549

Filename

5947549