ADAPTIVE VOICE AUTHENTICATION SYSTEM AND METHOD

• US 20170140760A1
• Filed: 03/09/2016
• Published: 05/18/2017
• Est. Priority Date: 11/18/2015
• Status: Active Grant

• Current Assignee: Uniphore Technologies, Inc. (Uniphore Software Systems Pvt Ltd.)
• Original Assignee: Uniphore Software Systems Co.
• Inventors: SACHDEV, Umesh
• Granted Patent: US 9,940,934 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 25/15 the extracted parameters being formant information
• CPC Class Codes: G10L 25/24 the extracted parameters being the cepstrum
• CPC Class Codes: G10L 25/75 for modelling vocal tract parameters

Abstract

An adaptive voice authentication system is provided. The adaptive voice authentication system includes an adaptive module configured to compare a feature quality index of the plurality of authentication features and the plurality of enrolment features and dynamically replace and store one or more enrolment features with one or more authentication features to form a plurality of updated enrolment features. The adaptive module is configured to generate an updated enrolment voice print model from the plurality of the updated enrolment features. The adaptive module is further configured to compare the updated enrolment voice print model with the previously stored enrolment voice print model and dynamically update the previously stored enrolment voice print model with the updated enrolment voice print model based on a model quality index.

Claims

1. An adaptive voice authentication system comprising:

a feature extractor configured to receive a user'"'"'s enrolment voice sample and a user'"'"'s authentication voice sample and configured to extract a plurality of enrolment features from the user'"'"'s enrolment voice sample and a plurality of authentication features from the user'"'"'s authentication voice sample;

wherein the user'"'"'s enrolment voice sample is an initial voice sample and the user'"'"'s authentication voice sample is a plurality of subsequent voice samples;

a voice print model generator configured to generate;

an enrolment voice print model from the plurality of enrolment features; and

an authentication voice print model from the plurality of authentication features;

an authentication module configured to receive the authentication voice print model and authenticate the user based on the enrolment voice print model;

a storage module configured to store the plurality of enrolment features, the plurality of authentication features, the enrolment voice print model and the authentication voice print model; and

an adaptive module configured to;

compare a feature quality index of the plurality of authentication features and the plurality of enrolment features and dynamically replace and store one or more enrolment features with one or more authentication features to form a plurality of updated enrolment features;

generate an updated enrolment voice print model from the plurality of updated enrolment features; and

compare the updated enrolment voice print model with the previously stored enrolment voice print model and dynamically update the previously stored enrolment voice print model with the updated enrolment voice print model based on a model quality index.

2. The adaptive voice authentication system of claim 1, wherein the plurality of enrolment features and the plurality of authentication features comprise vocal tract shape and length, short term and long term energy, fundamental pitch, formant features, speaking rate, prosody features, language and accent, nasality, cepstrum, emotional state or combinations thereof.

3. The adaptive voice authentication system of claim 1, further comprises a pre-processing module configured to improve the user'"'"'s enrolment voice sample and the user'"'"'s authentication voice sample by filtering a plurality of distortion elements.

4. The adaptive voice authentication system of claim 3, wherein the pre-processing module is configured to employ filtering operations comprising clipping, smoothening and amplifying the user'"'"'s enrolment voice sample and the user'"'"'s authentication voice sample to generate corresponding improved voice samples.

5. The adaptive voice authentication system of claim 1, wherein the adaptive module is configured to compare each authentication feature with all the enrolment features.

6. The adaptive voice authentication system of claim 5, wherein the enrolment features are updated when the feature quality index is higher than a feature threshold value.

7. The adaptive voice authentication system of claim 6, wherein the adaptive module is further configured to replace one or more of the plurality of enrolment features with authentication features when the feature quality index is higher than a feature threshold value.

8. The adaptive voice authentication system of claim 1, wherein the adaptive module is configured to compare the feature quality index of the plurality of features and the model quality index of voice print model each time an authentication is initiated.

9. The adaptive voice authentication system of claim 8, wherein

the feature quality index is determined based on signal to noise ratio, dynamic range level, loudness and consistency of the corresponding plurality of enrolment features and the authentication features;

and

the model quality index is determined based on signal to noise ratio, dynamic range level, loudness and consistency of the corresponding enrolment voice print model and the authentication voice print model.

10. The adaptive voice authentication system of claim 9, wherein the storage module is configured to store the feature quality index and the model quality index.

11. A method for dynamically updating one or more enrolment features and an enrolment voice print model, the method comprising:

receiving a user'"'"'s enrolment voice sample and a user'"'"'s authentication voice sample and extracting a plurality of enrolment features from the user'"'"'s enrolment voice sample and a plurality of authentication features from the user'"'"'s authentication voice sample;

generating an enrolment voice print model from the plurality of enrolment features; and

an authentication voice print model from the plurality of authentication features;

authenticating the user based on the enrolment voice print model;

storing the plurality of enrolment features, the plurality of authentication features, the enrolment voice print model and the authentication voice print model;

comparing each authentication feature with the plurality of enrolment features and dynamically replacing and storing one or more enrolment features with one or more authentication features based on a feature quality index;

generating an updated enrolment voice print model from the plurality of the updated enrolment features; and

comparing the updated enrolment voice print model with the previously stored enrolment voice print model and dynamically updating the previously stored enrolment voice print model with the updated enrolment voice print model based on a model quality index.

12. The method of claim 11, wherein the plurality of enrolment features and the plurality of authentication features comprise vocal tract shape and length, short term and long term energy, fundamental pitch, formant features, speaking rate, prosody features, language and accent, nasality, cepstrum, emotional state or combinations thereof.

13. The method of claim 11, further comprising improving the user'"'"'s enrolment voice sample and the user'"'"'s authentication voice sample by filtering a plurality of distortion elements;

wherein filtering operations comprises clipping, smoothening and amplifying the user'"'"'s enrolment voice sample and the user'"'"'s authentication voice sample to generate corresponding improved voice samples.

14. The method of claim 11, further comprising comparing each authentication feature with all the enrolment features and replacing one or more of the plurality of enrolment features with an authentication features based on the feature quality index.

15. The method of claim 14, wherein an enrolment feature is replaced when the feature quality index of the authentication feature is higher than a threshold value.