Phoneme assigning method
First Claim
1. A method of assigning phonemes (Pk) of a target language to a respective basic phoneme unit (PEZ(Pk)) of a set of basic phoneme units (PE1, PE2, . . . , PEN), which phoneme units are described by basic phoneme models, which models were generated based on available speech data of a source language, characterized by the following method steps:
- implementing at least two different speech data controlled assigning methods (1, 2) for assigning the phonemes (Pk) of the target language to a respective basic phoneme unit (PEi(Pk), PEj(Pk)), detecting whether the respective phoneme (Pk) was assigned to the same basic phoneme unit (PEi(Pk), PEj(Pk)) by a majority of the different speech data controlled assigning methods, selecting as the basic phoneme unit (PEz(Pk)) assigned to the respective phoneme (Pk) the basic phoneme unit (PEi(Pk), PEj(Pk)) assigned by the majority of the speech data controlled assigning methods (1, 2) insofar as a majority of the different speech data controlled assigning methods (1, 2) have a matching assignment, or, otherwise, selecting a basic phoneme unit (PEz(Pk)) from all the basic phoneme units (PEi(Pk), PEj(Pk)) which were assigned to the respective phoneme (Pk) by at least one of the different speech data controlled assigning methods (1, 2), while a similarity parameter is used in accordance with a symbol phonetic description of the phoneme (Pk) to be assigned and of the basic phoneme units (PEi(Pk), PEj(Pk)).
1 Assignment
0 Petitions
Accused Products
Abstract
A description is given of a method of assigning phonemes (Pk) of a target language to a respective basic phoneme unit (PEZ(Pk)) of a set of basic phoneme units (PE1, PE2, . . . , PEN) which are described by respective basic phoneme models, which models were generated via the use of available speech data of a source language. For this purpose, in a first step of the method at least two different speech data controlled assigning methods (1, 2) are used for assigning the phonemes (Pk) of the target language to a respective basic phoneme unit (PEi(Pk), PEj(Pk)). Subsequently, in a second step there is detected whether the respective phoneme (Pk) was correspondingly assigned to the same basic phoneme unit (PEi(Pk), PEj(Pk)) by a majority of the various speech data controlled assigning methods. If there is a largely matching assignment by the various speech data controlled assigning methods (1, 2), the basic phoneme unit (PEi(Pk), PEj(Pk)) assigned by the majority of the speech data controlled assigning methods (1, 2) is selected as the basic phoneme unit (PEz(Pk)) assigned to the respective phoneme (Pk). On the other hand, from all the basic phoneme units (PEi(Pk), PEj(Pk)) that were assigned to the respective phoneme (Pk) by at least one of the various speech data controlled assigning methods (1, 2), one basic phoneme unit is selected while a degree of similarity is used in accordance with a symbol-phonetic description of the assigned phoneme (Pk) and of the basic phoneme units (PEi(Pk), PEj(Pk)).
35 Citations
10 Claims
-
1. A method of assigning phonemes (Pk) of a target language to a respective basic phoneme unit (PEZ(Pk)) of a set of basic phoneme units (PE1, PE2, . . . , PEN), which phoneme units are described by basic phoneme models, which models were generated based on available speech data of a source language, characterized by the following method steps:
-
implementing at least two different speech data controlled assigning methods (1, 2) for assigning the phonemes (Pk) of the target language to a respective basic phoneme unit (PEi(Pk), PEj(Pk)), detecting whether the respective phoneme (Pk) was assigned to the same basic phoneme unit (PEi(Pk), PEj(Pk)) by a majority of the different speech data controlled assigning methods, selecting as the basic phoneme unit (PEz(Pk)) assigned to the respective phoneme (Pk) the basic phoneme unit (PEi(Pk), PEj(Pk)) assigned by the majority of the speech data controlled assigning methods (1, 2) insofar as a majority of the different speech data controlled assigning methods (1, 2) have a matching assignment, or, otherwise, selecting a basic phoneme unit (PEz(Pk)) from all the basic phoneme units (PEi(Pk), PEj(Pk)) which were assigned to the respective phoneme (Pk) by at least one of the different speech data controlled assigning methods (1, 2), while a similarity parameter is used in accordance with a symbol phonetic description of the phoneme (Pk) to be assigned and of the basic phoneme units (PEi(Pk), PEj(Pk)). - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
Specification