Large-vocabulary speech recognition: a system for the Italian language
IBM Journal of Research and Development
High level knowledge sources in usable speech recognition systems
Communications of the ACM
The cascade-correlation learning architecture
Advances in neural information processing systems 2
Understanding spontaneous speech: the Phoenix system
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Hi-index | 0.00 |
A standard semantic analyser accepting dictated sentences belonging to a grammar is used in a vocal information retrieving system. In this paper we mainly address the problem of managing sentences not in the grammar and errors from the speech recognizer. Three different methods are proposed, based respectively on alignment techniques, logical rules and neural networks. The results show that almost 85% of sentences out of grammar - even because of recognizer's errors - are correctly understood.