Method and apparatus for assembling a prediction list of name pronunciation variations for use during speech recognition
First Claim
1. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
- identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein the step of identifying the one or more of said languages as a potential origin of the proper name comprises the steps of;
determining one or more successive letter sequences included in an orthographic representation of said proper name;
for each of said successive letter sequences, computing a plurality of first probabilities corresponding to said plurality of languages, each of said first probabilities representative of a likelihood for said successive letter sequence to occur in the corresponding language; and
computing a plurality of second probabilities corresponding to each of said plurality of languages, each of said second probabilities based on a corresponding set of said first probabilities, and representative of a likelihood for said corresponding language to be an origin of said proper name.
2 Assignments
0 Petitions
Accused Products
Abstract
Multiple, yet plausible, pronunciations of a proper name are generated based on one or more potential language origins of the name, and based further on the context in which the name is being spoken—namely, on characteristics of the population of potential speakers. Conventional techniques may be employed to identify likely candidates for the language origin of the name, and the characteristics of the speaker population on which the generation of the pronunciations is further based may comprise, for example, the national origin of the speakers, the purpose of the speech, the geographical location of the speakers, or the general level of sophistication of the speaker population. Specifically, a method and apparatus is provided for generating a plurality of plausible pronunciations for a proper name, the method or apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method or apparatus comprising steps or means respectively for (a) identifying one or more of a plurality of languages as a potential origin of the proper name; and (b) generating a plurality of plausible pronunciations for the given proper name, one or more of the plurality of pronunciations based on the one or more identified languages, and the plurality of plausible pronunciations based further on one or more characteristics associated with the given population of speakers.
234 Citations
34 Claims
-
1. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein the step of identifying the one or more of said languages as a potential origin of the proper name comprises the steps of;
determining one or more successive letter sequences included in an orthographic representation of said proper name;
for each of said successive letter sequences, computing a plurality of first probabilities corresponding to said plurality of languages, each of said first probabilities representative of a likelihood for said successive letter sequence to occur in the corresponding language; and
computing a plurality of second probabilities corresponding to each of said plurality of languages, each of said second probabilities based on a corresponding set of said first probabilities, and representative of a likelihood for said corresponding language to be an origin of said proper name. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method of cenerating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with a person identified by said proper name.
-
-
13. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with one of said languages identified as a potential origin of said proper name.
-
-
14. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises a predetermined purpose of the speech utterances likely to be intended by individuals within the given population of speakers.
-
-
15. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises a geographical location from which individuals within the given population of speakers are likely to be located.
-
-
16. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with one or more languages other than the one or more languages identified as a potential origin of the proper name.
-
-
17. A method of generating a plurality of plausible pronunciations for a proper name, the method for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the method comprising the steps of:
-
identifying one or more of a plurality of languages as a potential origin of the proper name; and
generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein said proper name comprises an identity of a geographical location.
-
-
18. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein the means for identifying the one or more of said languages as a potential origin of the proper name comprises;
means for determining one or more successive letter sequences included in an orthographic representation of said proper name;
means, for computing, for each of said successive letter sequences, a plurality of first probabilities corresponding to said plurality of languages, each of said first probabilities representative of a likelihood for said successive letter sequence to occur in the corresponding language; and
means for computing a plurality of second probabilities corresponding to each of said plurality of languages, each of said second probabilities based on a corresponding set of said first probabilities, and representative of a likelihood for said corresponding language to be an origin of said proper name. - View Dependent Claims (19, 20, 21, 22, 23, 24, 25, 26, 27, 28)
-
-
29. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with a person identified by said proper name.
-
-
30. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with one of said languages identified as a potential origin of said proper name.
-
-
31. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises a predetermined purpose of the speech utterances likely to be intended by individuals within the given population of speakers.
-
-
32. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises a geographical location from which individuals within the given population of speakers are likely to be located.
-
-
33. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein one of said characteristics associated with said given population of speakers comprises familiarity by individuals within the given population of speakers with one or more languages other than the one or more languages identified as a potential origin of the proper name.
-
-
34. An apparatus for generating a plurality of plausible pronunciations for a proper name, the apparatus for use in performing speech recognition of speech utterances comprising the proper name by individuals within a given population of speakers, the apparatus comprising:
-
means for identifying one or more of a plurality of languages as a potential origin of the proper name; and
means for generating a plurality of plausible pronunciations for the given proper name, one or more of said plurality of pronunciations based on the one or more identified languages, and said plurality of plausible pronunciations based further on one or more characteristics associated with said given population of speakers, wherein said proper name comprises an identity of a geographical location.
-
Specification