Word competition models in voice recognition
First Claim
Patent Images
1. A method for recognizing speech patterns, the method comprising:
- segmenting a word into a string of consecutive phonemes;
storing a plurality of sequences of the phonemes, at least one of the sequences omitting at least one phoneme that is preceding a last one of the phonemes in the string and succeeding a first one of the phonemes in the string;
comparing an utterance with the plurality of sequences of phonemes; and
determining if a match exists between the utterance and a particular one of the sequences of phonemes.
7 Assignments
0 Petitions
Accused Products
Abstract
A system and method relate to voice recognition software, and more particularly to voice recognition tutoring software to assist in reading development.
-
Citations
31 Claims
-
1. A method for recognizing speech patterns, the method comprising:
-
segmenting a word into a string of consecutive phonemes;
storing a plurality of sequences of the phonemes, at least one of the sequences omitting at least one phoneme that is preceding a last one of the phonemes in the string and succeeding a first one of the phonemes in the string;
comparing an utterance with the plurality of sequences of phonemes; and
determining if a match exists between the utterance and a particular one of the sequences of phonemes. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method comprising:
-
segmenting a word into a string of consecutive phonemes;
categorizing the word according to predefined levels of pronunciation by associating certain sequences of the phonemes with a pronunciation level for the word the sequences being different for the plurality of levels. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. A speech-recognizing device configured to:
-
segment a word into a string of consecutive phonemes;
store a plurality of sequences of the phonemes, at least one of the sequences omitting at least one phoneme that is preceding a last one of the phonemes in the string and succeeding a first one of the phonemes in the string;
compare an utterance with the plurality of sequences of phonemes; and
determine if a match exists between the utterance and a particular one of the sequences of phonemes. - View Dependent Claims (17, 18)
-
-
19. A device configured to:
-
segment a word into a string of consecutive phonemes; and
categorize the word according to predefined levels of pronunciation by associating certain sequences of the phonemes with a pronunciation level for the word the sequences being different for the plurality of levels. - View Dependent Claims (20, 21, 22, 23)
-
-
24. A computer program product, tangibly embodied in an information carrier, for executing instructions on a processor, the computer program product being operable to cause a machine to:
-
segment a word into a string of consecutive phonemes;
store a plurality of sequences of the phonemes, at least one of the sequences omitting at least one phoneme that is preceding a last one of the phonemes in the string and succeeding a first one of the phonemes in the string;
compare an utterance with the plurality of sequences of phonemes; and
determine if a match exists between the utterance and a particular one of the sequences of phonemes. - View Dependent Claims (25, 26)
-
-
27. A computer program product, tangibly embodied in an information carrier, for executing instructions on a processor, the computer program product being operable to cause a machine to:
-
segment a word into a string of consecutive phonemes;
categorize the word according to predefined levels of pronunciation by associating certain sequences of the phonemes with a pronunciation level for the word the sequences being different for the plurality of levels. - View Dependent Claims (28, 29, 30, 31)
-
Specification