Method and apparatus for speech recognition using domain ontology
AssigneeElectronics and Telecommunications Research Institute
InventorsSeung YUN, Soo Jong Lee, Jeong Se Kim, Il Bin Lee, Jun Park, Sang Kyu Park
Life of this patent
Estimating the term…
Abstract
A speech recognition method using a domain ontology includes: constructing domain ontology DB; forming a speech recognition grammar using the formed domain ontology DB; extracting a feature vector from a speech signal; modeling the speech signal using an acoustic model. The method performs speech recognition by using the acoustic model, the speech recognition dictionary and the speech recognition grammar on the basis of the feature vector.
Claims16
A speech recognition method using a domain ontology, comprising:
- constructing domain ontology DB;
- forming a speech recognition grammar using the constructed domain ontology DB;
- extracting a feature vector from a speech signal;
- modeling the speech signal by using an acoustic model;
- and
- recognizing speech by using the acoustic model, the speech recognition dictionary and the speech recognition grammar on the basis of the feature vector.
A speech recognition apparatus using a domain ontology, comprising:
- a domain ontology unit for constructing domain ontology DB;
- a grammar forming unit for forming a speech recognition grammar using the formed domain ontology DB;
- an vector extracting unit for extracting a feature vector from a speech signal;
- a model unit for modeling the speech signal using an acoustic model;
- and
- a speech recognizing unit for recognizing speech using the acoustic model, the speech recognition dictionary and the speech recognition grammar on the basis of the feature vector.
Dependencies are inferred from the claim text.