Chinese Dialect Identification Based on Genetic Algorithm for Discriminative Training of Bigram Model

Wuei-He TSAI  Wen-Whei CHANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E83-D   No.12   pp.2183-2185
Publication Date: 2000/12/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
Chinese dialect identification,  minimum classification error,  generalized probabilistic descent algorithm,  genetic algorithm,  

Full Text: PDF(145.9KB)>>
Buy this Article

A minimum classification error formulation based on genetic algorithm is proposed for discriminative training of the bigram language model. Results of Chinese dialect identification were reported which demonstrate performance improvement with use of the genetic algorithm over the generalized probabilistic descent algorithm.