Name pronounciation by synthesizer
First Claim
1. A method for determining if any of a plurality of language groups may be identified, or removed from consideration, as a language group of origin for an input word using a programmable computer, the method comprising the steps of:
- (a) applying a set of filter rules, which are stored in memory means of the programmable computer, to predetermined substrings of graphemes of the input word to determine if there is a match between one of the substrings and one of the filter rules of a particular language group which positively identifies the input word as being part of a that language group, or if there is an absence of a match between any of the predetermined substrings of graphemes of the input word and the filter rules for a particular language group of the plurality of language groups so as to eliminate that particular language group from consideration as a language group of origin of the input word, with the filter rules for each language group of the plurality of language groups including N graphemes where 1<
N≦
R and R=the number of graphemes in the input word; and
(b) generating a representative indicator of the language group of origin of the input word if there is a match or generating a list of possible language groups of origin for the input word according to the filter rules when there is the absence of a match.
2 Assignments
0 Petitions
Accused Products
Abstract
An apparatus and method for correctly pronouncing proper names from text using a computer provides a dictionary which performs an initial search for the name. If the name is not in the dictionary, it is sent to a filter which either positively identifies a single language group or eliminates one or more language groups as the language group of origin for that word. When the filter cannot positively identify the language group of origin for the name, a list of possible language groups is sent to a grapheme analyzer which precedes a trigram analyzer. Using grapheme analysis, the most probable language group of origin for the name is determined and sent to a language-sensitive letter-to-sound section. In this section, the name is compared with language-sensitive rules to provide accurate phonemics and stress information for the name. The phonemics (including stress information) are sent to a voice realization unit for audio output of the name.
292 Citations
9 Claims
-
1. A method for determining if any of a plurality of language groups may be identified, or removed from consideration, as a language group of origin for an input word using a programmable computer, the method comprising the steps of:
-
(a) applying a set of filter rules, which are stored in memory means of the programmable computer, to predetermined substrings of graphemes of the input word to determine if there is a match between one of the substrings and one of the filter rules of a particular language group which positively identifies the input word as being part of a that language group, or if there is an absence of a match between any of the predetermined substrings of graphemes of the input word and the filter rules for a particular language group of the plurality of language groups so as to eliminate that particular language group from consideration as a language group of origin of the input word, with the filter rules for each language group of the plurality of language groups including N graphemes where 1<
N≦
R and R=the number of graphemes in the input word; and(b) generating a representative indicator of the language group of origin of the input word if there is a match or generating a list of possible language groups of origin for the input word according to the filter rules when there is the absence of a match. - View Dependent Claims (2)
-
-
3. A method for generating correct phonemics for an input word according to a language group of origin using a programmable computer, the method comprising the steps of:
-
(a) inputting the input word to the programmable computer; (b) searching a dictionary stored in memory means of the programmable computer for a match between the input word and a dictionary entry, with each dictionary entry including a word and phonemics for that word, and sending contents of a dictionary entry in which the word of that entry matches the input word to a voice realization means for pronunciation, or processing the input word according to the step (c) if there is an absence of a match between the input word and a dictionary entry; (c) applying a set of filter rules, which are stored in memory means of the programmable computer, to predetermined substrings of graphemes of the input word, with the filter rules for each language group of the plurality of language groups including N graphemes where 1<
N≦
R and R=the number of graphemes in the input word, and with the applying step being for,(1) determining if there is a match between one of the predetermined set of graphemes of the input word substrings and one of the filter rules identifiable with one of the plurality of language groups which positively identifies the input word as being part of a particular language group and thereafter processing input word according to step (d), or (2) determining if there is an absence of a match between any of the predetermined substrings of graphemes of the input word and the filter rules for a particular language group of the plurality of language groups so as to eliminate that particular language group from consideration as a language group of origin of the input word and if there is the absence of match, generating a list of possible language groups of origin of the input word, and thereafter processing the input word according to step (e); (d) transmitting the input word and a language tag indicative of the language group of origin identified at substep (c) (1) to a letter-to-sound means in the programmable computer, with the letter-to-sound means including letter-to-sound rules, and further processing the input word according to step (g); (e) transmitting the input word and the list of possible language groups of origin of the input word to a grapheme analyzer in the programmable computer and determining a most probable language group of origin from the list generated at substep (c) (2) by examining graphemes of the input word of a predetermined length; (f) transmitting the input word and the most probable language group of origin determined at step (e) to the letter-to-sound means; (g) generating in the letter-to-sound means according to the letter-to-sound rules segmental phonemics for the input word and further processing the input word according to step (h); (h) transmitting the segmental phonemics and a language tag to a stress assignment means of the programmable computer and generating in the stress assignment means stress assignment information for the input word; and (i) transmitting the segmental phonemics and the stress assignment information to the voice realization means. - View Dependent Claims (4, 5, 6, 7)
-
-
8. An apparatus that is capable of being embodied in a programmable computer for determining if any of a plurality of language groups may be identified, or removed from consideration, as a language group of origin for a given word, comprising:
-
filter rule store means for storing filter rules; comparator means that are used for determining if there is a match between a predetermined substring of graphemes of an input word and one of the filter rules identifiable with one of a plurality of language groups which positively identifies the input word as being part of a specific language group, or if there is an absence of a match between any of the predetermined substrings of graphemes of the input word and the filter rules of a particular language group of the plurality of language groups so as to eliminate that particular language group from consideration as a language group from consideration as a language group of origin of the input word, with the filter rules for each language group of the plurality of language groups including N graphemes where 1 <
N≦
R and R=the number of graphemes in the input word; andoutput means of the comparator means for outputting therefrom at least a list of possible language groups of origin if there is an absence of a match between a predetermined substring of graphemes and the input word, or the language group of origin if there is a match between a predetermined substring of graphemes and the input word.
-
-
9. A method for processing an input word before trigram analysis for determining if any of a plurality of language groups may be identified, or eliminated from consideration, as a language group of origin for the input word, the method comprising applying a set of filter rules, which are stored in memory means of a programmable computer, to predetermined substrings of graphemes of the input word to determine if there is a match between one of the substrings and one of the filter rules identifiable with one of the plurality of language groups which positively identifies the input word as being part of a specific language group, or if there is an absence of a match between any of the predetermined substrings of graphemes of the input word and the filter rules for a particular language group of the plurality of language groups so as to eliminate that particular language group from consideration as a language group of origin of the input word, with the filter rules for each language group of the plurality of language groups including N graphemes where 1≦
- N≦
R and R =the number of graphemes in the input word.
- N≦
Specification