Method for recognizing speech using eigenpronunciations
First Claim
1. Method for recognizing speech, wherein a pronunciation space (PS) of possible pronunciation rules and/or sets thereof is provided, wherein in said pronunciation space (PS) an at least approximative set of pronunciation rules (APR) is determined and/or generated in accordance with a current pronunciation (CP) and/or accent of a current speaker, and wherein at least one current lexicon (CL) or a dictionary of pronunciation variants which is employed for recognition is adapted to said current speaker by applying at least said approximative set of pronunciation rules (APR) to it, thereby at least including speaker specific pronunciation variants to said current lexicon (CL).
2 Assignments
0 Petitions
Accused Products
Abstract
To increase the recognition rate and quality in a process of recognizing speech an approximative set of pronunciation rules (APR) for a current pronunciation (CP) of a current speaker is determined in a given pronunciation space (PS) and then applied to a current pronunciation lexicon (CL) so as to perform a speaker specific adaptation of said current lexicon (CL).
40 Citations
20 Claims
-
1. Method for recognizing speech,
wherein a pronunciation space (PS) of possible pronunciation rules and/or sets thereof is provided, wherein in said pronunciation space (PS) an at least approximative set of pronunciation rules (APR) is determined and/or generated in accordance with a current pronunciation (CP) and/or accent of a current speaker, and wherein at least one current lexicon (CL) or a dictionary of pronunciation variants which is employed for recognition is adapted to said current speaker by applying at least said approximative set of pronunciation rules (APR) to it, thereby at least including speaker specific pronunciation variants to said current lexicon (CL).
Specification