Speech recognition performance improvement method and speech recognition device
First Claim
Patent Images
1. A method for use with a speech recognition device for improving speech recognition performance, said method comprising:
- generating, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose start positions of non-speech regions differ;
performing speech recognition using each of said pieces of speech data; and
identifying the most numerous recognized result from among the plurality of obtained recognized results.
1 Assignment
0 Petitions
Accused Products
Abstract
Speech recognition performance is improved without changing a speech recognition engine. A speech data generation section generates, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose starting positions of the non-speech regions differ. A speech recognition engine performs speech recognition by using each of the pieces of speech data. A totaling/comparison section provides the most numerous recognized result from among a plurality of obtained recognized results.
24 Citations
20 Claims
-
1. A method for use with a speech recognition device for improving speech recognition performance, said method comprising:
-
generating, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose start positions of non-speech regions differ;
performing speech recognition using each of said pieces of speech data; and
identifying the most numerous recognized result from among the plurality of obtained recognized results. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A speech recognition device comprising:
-
a speech data generation section for generating, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose start positions of non-speech regions differ;
a speech recognition engine for performing speech recognition on each of said pieces of speech data; and
a recognized result selection section for selecting the most numerous recognized result from among the plurality of obtained recognized results. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A speech recognition device for improving speech recognition performance, said speech recognition device comprising:
-
a speech data generation section for generating, from speech data for which speech recognition is to be performed, a plurality of pieces of speech data whose start positions of non-speech regions differ;
a speech recognition engine, for performing speech recognition on the speech data, provided for each of a plurality of pieces of speech data whose start positions of non-speech regions differ; and
a recognized result selection section for selecting and providing as an output the most numerous recognized result from among the plurality of obtained recognized results. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification