A modified HME architecture for text-dependent speaker identification

Author

Chen, Ke ; Xie, Dahong ; Chi, Huisheng

Author_Institution

Nat. Lab. of Machine Perception, Beijing Univ., China

Volume

7

Issue

5

fYear

1996

fDate

9/1/1996 12:00:00 AM

Firstpage

1309

Lastpage

1313

Abstract

A modified hierarchical mixtures of experts (HME) architecture is presented for text-dependent speaker identification. A new gating network is introduced to the original HME architecture for the use of instantaneous and transitional spectral information in text-dependent speaker identification. The statistical model underlying the proposed architecture is presented and learning is treated as a maximum likelihood problem; in particular, an expectation-maximization (EM) algorithm is also proposed for adjusting the parameters of the proposed architecture. An evaluation has been carried out using a database of isolated digit utterances by 10 male speakers. Experimental results demonstrate that the proposed architecture outperforms the original HME architecture in text-dependent speaker identification

Keywords

feature extraction; neural nets; speaker recognition; expectation-maximization algorithm; gating network; isolated digit utterances; male speakers; maximum likelihood problem; modified hierarchical mixtures of experts architecture; statistical model; text-dependent speaker identification; Databases; Feature extraction; Information science; Neural networks; Neurons; Statistics; Testing;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.536325

Filename

536325