Automatic speech translation based on the semantic structure
- 24 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 658-661
- https://doi.org/10.1109/icslp.1996.607447
Abstract
This paper describes a system for the semantic-based translation of spoken or written limited-domain utterances. The semantic structure as output of a semantic decoder serves as the interlin- gua-level. A word chain generator combined with a linguistic post-processor produces the according word chain in the target language. Both the semantic decoder and the word chain genera- tor work with pure stochastic and trainable knowledge bases. The grammatical features of certain words can be easily extracted by the help of both the word chain and the semantic structure.Keywords
This publication has 5 references indexed in Scilit:
- An efficient top-down parsing algorithm for understanding speech by using stochastic syntactic and semantic modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Concept-based speech translationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A speech understanding system based on statistical representation of semanticsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- An efficient context-free parsing algorithmCommunications of the ACM, 1970