Method and apparatus for improving the transcription accuracy of speech recognition software
First Claim
1. A method for operating a computerized, speech recognition system, said speech recognition system including a default vocabulary database and an adjunct vocabulary database, said adjunct vocabulary database having vocabulary elements previously used within said speech recognition system, said vocabulary elements within said adjunct vocabulary database including at least one tag associated with a previous use of said vocabulary element within said system, said tag having associated weighting information, said method comprising:
- providing speech input to said speech recognition system, said speech recognition system providing a set of vocabulary matching elements based on said speech input, said set of vocabulary matching elements having associated default weightings;
creating a virtual sub-vocabulary from said adjunct vocabulary database based on said tag;
modifying said default weightings of said set of vocabulary matching elements according to said weighting information associated with said tags; and
selecting a vocabulary element from said set of vocabulary matching elements as a match for said speech input based on said modified weighting within said modified, set of vocabulary matching elements.
0 Assignments
0 Petitions
Accused Products
Abstract
A virtual vocabulary database is provided for use with a with a particular user database as part of a speech recognition system. Vocabulary elements within the virtual database are imported from the user database and are tagged to include numerical data corresponding to the historical use of the vocabulary element within the user database. For each speech input, potential vocabulary element matches from the speech recognition system are provided to the virtual database software which creates virtual sub-vocabularies from the criteria according to predefined criteria templates. The software then applies vocabulary element weighting adjustments according to the virtual sub-vocabulary weightings and applies the adjustment to the default weighting provided by the speech recognition system. The modified weightings are returned with the associated vocabulary elements to the speech engine for selection of an appropriate match to the input speech.
303 Citations
10 Claims
-
1. A method for operating a computerized, speech recognition system, said speech recognition system including a default vocabulary database and an adjunct vocabulary database, said adjunct vocabulary database having vocabulary elements previously used within said speech recognition system, said vocabulary elements within said adjunct vocabulary database including at least one tag associated with a previous use of said vocabulary element within said system, said tag having associated weighting information, said method comprising:
-
providing speech input to said speech recognition system, said speech recognition system providing a set of vocabulary matching elements based on said speech input, said set of vocabulary matching elements having associated default weightings; creating a virtual sub-vocabulary from said adjunct vocabulary database based on said tag; modifying said default weightings of said set of vocabulary matching elements according to said weighting information associated with said tags; and selecting a vocabulary element from said set of vocabulary matching elements as a match for said speech input based on said modified weighting within said modified, set of vocabulary matching elements. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A speech recognition system having a default vocabulary database, said system comprising:
-
an adjunct vocabulary database, said adjunct vocabulary database having vocabulary elements previously used within said speech recognition system, said vocabulary elements within said adjunct vocabulary database including at least one tag associated with a previous use of said vocabulary element within said system; a prioritization module for modifying a weighting of at least one element of said default vocabulary database elements according to said tags; and an interface module for returning said modified weighting associated with said element of said default vocabulary database to said speech recognition system. - View Dependent Claims (7, 8, 9)
-
-
10. A non-transitory computer readable media having executable instructions for causing a processor to perform a method for operating a computerized, speech recognition system, said speech recognition system including a default vocabulary database and an adjunct vocabulary database, said adjunct vocabulary database having vocabulary elements previously used within said speech recognition system, said vocabulary elements within said adjunct vocabulary database including at least one tag associated with a previous use of said vocabulary element within said system, said tag having associated weighting information, said method comprising:
-
providing speech input to said speech recognition system, said speech recognition system providing a set of vocabulary matching elements based on said speech input, said set of vocabulary matching elements having associated default weightings; creating a virtual sub-vocabulary from said adjunct vocabulary database based on said tag; modifying said default weightings of said set of vocabulary matching elements according to said weighting information associated with said tags; and selecting a vocabulary element from said set of vocabulary matching elements as a match for said speech input based on said modified weighting within said modified, set of vocabulary matching elements.
-
Specification