SYSTEM, METHOD AND DEVICE FOR LANGUAGE EDUCATION THROUGH A VOICE PORTAL
0 Assignments
0 Petitions
Accused Products
Abstract
A method of teaching pronunciation is provided which includes communicating by a voice portal server to a user a model word and detecting a response by the user to the voice portal server. The method also includes comparing the response word to the model word and determining a confidence level based on the comparison of the response word to the model word. The method further includes comparing an acceptance limit to the confidence level and confirming a correct pronunciation of the model word if the confidence level one of equals and exceeds the acceptance limit.
276 Citations
34 Claims
-
1-7. -7. (canceled)
-
8. A system for teaching a user pronunciation, comprising:
-
a voice portal arrangement; a communication arrangement adapted to be coupled with the voice portal arrangement; an application server adapted to be coupled with the voice portal arrangement; and a geo-server for determining a location; wherein; the geo-server determines a location of the user and a dominant language and a regional dialect prevailing at the determined location of the user; the voice portal arrangement provides the user a prompt in the determined regional dialect of the dominant language, and compares at least one word spoken by the user in response to the prompt to determine a confidence level; the at least one word spoken by the user is associated in memory with a plurality of valid pronunciations; and one of the plurality of valid pronunciations used by the user for the at least one word spoken by the user is determined to be incorrect based on the regional dialect. - View Dependent Claims (9, 10, 11, 12, 13, 28, 29, 30, 31, 32, 33, 34)
-
-
14. A method of teaching a user a language, comprising:
-
determining a location of the user and a dominant language and a regional dialect prevailing at the determined location of the user; communicating a prompt in the determined regional dialect of the dominant language to a user by a voice portal; detecting a response provided by the user, the response being provided to the voice portal; parsing the response into at least one uttered phrase, each of the at least one uttered phrase being associated with at least one corresponding slot; comparing each of the at least one uttered phrase with at least one stored phrase, the at least one stored phrase being associated with the at least one corresponding slot; determining a confidence level by comparing each of the at least one uttered phrase with each of the at least one stored phrase; comparing each determined confidence level to an associated acceptance limit, the associated acceptance limit being associated with each of the at least one stored phrase; and confirming that each of the at least one uttered phrase corresponds to the at least one stored phrase if the confidence level is not less than the associated acceptance limit; wherein a pronunciation of the at least one uttered phrase is determined (a) to be one of a stored plurality of valid pronunciations, and (b) to be incorrect based on the regional dialect. - View Dependent Claims (15, 16, 17, 20, 21, 22, 23, 24, 25, 26)
-
-
18-19. -19. (canceled)
-
27. A non-transitive computer-readable medium, having a program executable on a processor arrangement, to perform a method, the method comprising:
-
determining a location of the user and a dominant language and a regional dialect prevailing at the determined location of the user; communicating a prompt in the determined regional dialect of the dominant language to a user by a voice portal; detecting a response provided by the user, the response being provided to the voice portal; parsing the response into at least one uttered phrase, each of the at least one uttered phrase being associated with at least one corresponding slot; comparing each of the at least one uttered phrase with at least one stored phrase, the at least one stored phrase being associated with the at least one corresponding slot; determining a confidence level by comparing each of the at least one uttered phrase with each of the at least one stored phrase; comparing each determined confidence level to an associated acceptance limit, the associated acceptance limit being associated with each of the at least one stored phrase; and confirming that each of the at least one uttered phrase corresponds to the at least one stored phrase if the confidence level is not less than the associated acceptance limit; wherein a pronunciation of the at least one uttered phrase is determined (a) to be one of a stored plurality of valid pronunciations, and (b) to be incorrect based on the regional dialect.
-
Specification