Automatic speech translation based on the semantic structure

Author

Müller, Johannes ; Stahl, Holger ; Lang, Manfred

Author_Institution

Inst. for Human-Machine-Commun., Munchen Univ. of Technol., Germany

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

658

Abstract

Describes a system for the semantic-based translation of spoken or written limited-domain utterances. The semantic structure, as the output of a semantic decoder, serves as the interlingua level. A word-chain generator combined with a linguistic post-processor produces the corresponding word chain in the target language. Both the semantic decoder and the word chain generator work with pure stochastic and trainable knowledge bases. The grammatical features of certain words can be easily extracted with the aid of both the word chain and the semantic structure

Keywords

decoding; language translation; linguistics; natural languages; speech recognition; automatic speech translation; grammatical feature extraction; inflectional model; interlingua level; language production; limited-domain utterances; linguistic post-processor; semantic decoder; semantic model; semantic structure; speech understanding; spoken utterances; stochastic knowledge bases; syntactic model; trainable knowledge bases; word-chain generator; written utterances; Decoding; Graphics; Logic; Natural languages; Speech synthesis; Stochastic processes; Tin;

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.1996.607447

Filename

607447