METHOD AND APPARATUS FOR ALIGNING TEXTS
First Claim
Patent Images
1. A method for aligning texts, comprising the steps of:
- acquiring a target text and a reference text; and
aligning the target text and the reference text at word level based on phoneme similarity;
wherein the above steps are carried out by a programmed data processing system.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and apparatus for aligning texts. The method includes acquiring a target text and a reference text and aligning the target text and the reference text at word level based on phoneme similarity. The method can be applied to automatically archiving a multimedia resource and a method of automatically searching a multimedia resource.
324 Citations
26 Claims
-
1. A method for aligning texts, comprising the steps of:
-
acquiring a target text and a reference text; and aligning the target text and the reference text at word level based on phoneme similarity; wherein the above steps are carried out by a programmed data processing system. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. An apparatus for aligning texts, comprising:
-
an input module for acquiring a target text and a reference text; and a word alignment module for aligning the target text and the reference text at word level based on phoneme similarity. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24)
-
-
25. A method for archiving a multimedia resource, comprising the steps of:
-
acquiring an original multimedia resource and a reference text; recognizing speech data in the original multimedia resource to generate a target text; aligning the target text and the reference text at word level based on phoneme similarity; establishing a temporal link between the speech and the reference text based on alignment of the target text and the reference text; and adding the temporal link to the original multimedia resource to generate a new multimedia resource archive file; wherein at least one of the foregoing steps is carried out by a programmed data processing machine.
-
-
26. A method for searching a multimedia resource, wherein the multimedia resource comprises speech data and its reference text, comprising:
-
acquiring a key word for search; acquiring a multimedia resource, the multimedia resource comprising a reference text and a target text obtained through recognizing speech data in the multimedia resource, the reference text and the target text being aligned at word level based on phoneme similarity, and a temporal link being established between the reference text and the speech data based on the alignment; searching and identifying the key word in the reference text; and locating the part of the multimedia resource corresponding to the key word in the multimedia resource based on the location of the identified key word in the reference text and based on the temporal link; wherein at least one of the foregoing steps is carried out by a programmed data processing machine.
-
Specification