Learning new words from spontaneous speech
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 590-591 vol.2
- https://doi.org/10.1109/icassp.1993.319377
Abstract
The authors describe the design of a system to learn new words from spontaneous speech input, and present an initial experiment on detecting the new words to be learned. Learning a new word involves detecting an out-of-vocabulary word in the input, determining its meaning, and adding the word to the system lexicon and grammars. Such learning would enable later recognition, parsing, and interpretation of the new words.Keywords
This publication has 4 references indexed in Scilit:
- Understanding spontaneous speech: the Phoenix systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Automatic modeling for adding new words to a large-vocabulary continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Towards speech recognition without vocabulary-specific trainingPublished by Association for Computational Linguistics (ACL) ,1989
- POLITICS: Automated ideological reasoningCognitive Science, 1978