The application of discriminative training techniques in LID system fusion

Author

Hou, Tao ; Zhang, Weiqiang ; Liu, Jia

Author_Institution

Dept. of Electron. Eng., Tsinghua Univ., Beijing

fYear

2008

fDate

7-9 July 2008

Firstpage

1457

Lastpage

1460

Abstract

This paper reports an approach to language identification (LID) system fusion using discriminative training. Maximum mutual information (MMI) training for Gaussian mixture model is introduced to the standard LDA-GMM fusion framework. Experimental results show that the proposed fusion scheme outperforms the maximum likelihood (ML) trained backend of LID system. The impact of number of Gaussian mixtures on fusion performance is also discussed.

Keywords

Gaussian processes; learning (artificial intelligence); maximum likelihood estimation; sensor fusion; Gaussian mixture model; discriminative training techniques; language identification system fusion; maximum likelihood training; maximum mutual information; Gaussian distribution; Linear discriminant analysis; Mutual information; NIST; Natural languages; Pattern recognition; Power system modeling; Space technology; Speech recognition; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-1723-0

Electronic_ISBN

978-1-4244-1724-7

Type

conf

DOI

10.1109/ICALIP.2008.4590126

Filename

4590126

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2425052