Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches

Author

Huang, Chien-Lin ; Wu, Chung-Hsien ; Li, Haizhou ; Hsieh, Chia-Hsin ; Ma, Bin

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan

fYear

2008

fDate

June 23 2008-April 26 2008

Firstpage

1097

Lastpage

1100

Abstract

This study presents a novel approach to unsupervised pronunciation grammar growing for non-native speech recognition. Unsupervised pronunciation grammar growing includes pronunciation variation graph construction and non-native grammar generation. Knowledge-based and data-driven approaches are considered for variation graph construction. The measurement of confidence and support is used for grammar selection. Experiments show that unsupervised pronunciation grammar growing is suitable for the improvement of non-native speech recognition.

Keywords

grammars; graph theory; speech recognition; knowledge-based-data-driven approaches; nonnative speech recognition; unsupervised pronunciation grammar; variation graph construction; Automatic speech recognition; Computer science; Data engineering; Frequency; Hidden Markov models; Knowledge engineering; Man machine systems; Natural languages; Speech analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2008 IEEE International Conference on

Conference_Location

Hannover

Print_ISBN

978-1-4244-2570-9

Electronic_ISBN

978-1-4244-2571-6

Type

conf

DOI

10.1109/ICME.2008.4607630

Filename

4607630