Verification score normalization in a speaker voice recognition device
First Claim
1. A device for automatically recognizing the voice of a speaker authorized to access an application, said device comprising means for generating beforehand, during a learning phase, parameters of an acceptance voice model relative to a voice segment spoken by said authorized speaker and parameters of a rejection voice model, means for normalizing by means of normalization parameters a speaker verification score depending on the likelihood ratio between a voice segment to be tested and said acceptance model and rejection model for thereby deriving a normalized verification score, and means for comparing said normalized verification score to a first threshold in order to authorize access to the application by the speaker who spoke said voice segment to be tested only if the normalized verification score is at least as high as the first threshold, and means for updating at least one of said normalization parameters as a function of a preceding value of said one normalization parameter and the speaker verification score on each voice segment test only if the normalized verification score is at least equal to a second threshold that exceeds said first threshold.
1 Assignment
0 Petitions
Accused Products
Abstract
During a learning phase, a speech recognition device generates parameters of an acceptance voice model relating to a voice segment spoken by an authorized speaker and a rejection voice model. It uses normalization parameters to normalize a speaker verification score depending on the likelihood ratio of a voice segment to be tested and the acceptance model and rejection model. The speaker obtains access to a service application only if the normalized score is above a threshold. According to the invention, a module updates the normalization parameters as a function of the verification score on each voice segment test only if the normalized score is above a second threshold.
49 Citations
17 Claims
- 1. A device for automatically recognizing the voice of a speaker authorized to access an application, said device comprising means for generating beforehand, during a learning phase, parameters of an acceptance voice model relative to a voice segment spoken by said authorized speaker and parameters of a rejection voice model, means for normalizing by means of normalization parameters a speaker verification score depending on the likelihood ratio between a voice segment to be tested and said acceptance model and rejection model for thereby deriving a normalized verification score, and means for comparing said normalized verification score to a first threshold in order to authorize access to the application by the speaker who spoke said voice segment to be tested only if the normalized verification score is at least as high as the first threshold, and means for updating at least one of said normalization parameters as a function of a preceding value of said one normalization parameter and the speaker verification score on each voice segment test only if the normalized verification score is at least equal to a second threshold that exceeds said first threshold.
-
11. Apparatus for automatically recognizing the voice of a speaker authorized to access an application, said apparatus comprising a processor arrangement for:
- (a) storing parameters of an acceptance voice model and parameters of a rejection voice model, the parameters of the acceptance and rejection voice models being stored in the processor arrangement before the processor arrangement automatically recognizes the voice, the parameters of the acceptance voice model being relative to a voice segment spoken by said authorized speaker, (b) normalizing, with the aid of normalization parameters, a speaker verification score depending on the likelihood ratio between a voice segment to be tested and said acceptance model and rejection model for thereby deriving a normalized verification score, (c) comparing said normalized verification score to a first threshold, (d) authorizing access to the application by the speaker who spoke said voice segment to be tested only if (c) indicates the normalized verification score is at least as high as the first threshold, and (e) updating at least one of said normalization parameters as a function of a preceding value of said one normalization parameter and the speaker verification score on each voice segment test only if the normalized verification score is at least equal to a second threshold that exceeds said first threshold.
- View Dependent Claims (12, 13, 14, 15)
-
16. A method of recognizing the voice of a speaker authorized to access an application, said method comprising:
- generating beforehand, during a learning phase, parameters of an acceptance voice model relative to a voice segment spoken by said authorized speaker and parameters of a rejection voice model;
normalizing, with the aid of normalization parameters, a speaker verification score depending on the likelihood ratio between a voice segment to be tested and said acceptance model and rejection model to thereby derive a normalized verification score;
comparing said normalized verification score to a first threshold;
authorizing access to the application by the speaker who spoke said voice segment to be tested only if the comparing step indicates normalized verification score is at least as high as the first threshold; and
updating at least one of said normalization parameters as a function of a preceding value of said one normalization parameter and the speaker verification score on each voice segment test only if the normalized verification score is at least equal to a second threshold that exceeds said first threshold. - View Dependent Claims (17)
- generating beforehand, during a learning phase, parameters of an acceptance voice model relative to a voice segment spoken by said authorized speaker and parameters of a rejection voice model;
Specification