Language identification with inaccurate string matching

Author

Berkling, Kay M. ; Barnard, Etienne

Author_Institution

Center for Spoken Language Understanding, Graduate Inst. of Sci. & Technol., Beaverton, OR, USA

Volume

3

fYear

1996

fDate

3-6 Oct 1996

Firstpage

1796

Abstract

We describe a system designed to recognize the language of an utterance spoken by any native speaker over the telephone. The current approach extends our previous work on language identification based on sequences of speech units (K. Berkling and E. Barnard, 1995). To improve performance we extend this work to allow for inaccurate matches of such sequences. Results are reported for distinguishing between English and German. The strength of this algorithm lies in the generalizability from training to test set. We have obtained a means of discriminating between languages based on statistical derivations. Matching sequences inaccurately in a controlled manner allows us to account for variabilities within languages without sacrificing cross language discrimination

Keywords

natural languages; speech recognition; statistical analysis; string matching; English; German; cross language discrimination; inaccurate matches; inaccurate string matching; language identification; native speaker; speech units; statistical derivations; Context modeling; Cultural differences; Feedforward neural networks; Natural languages; Neural networks; Robustness; Speech processing; Speech recognition; System analysis and design; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607978

Filename

607978