Device, system, and method of liveness detection utilizing voice biometrics

Patent metadata

Field	Value
Publication number	US-9484037-B2
Application number	US-201414524214-A
Country	US
Kind code	B2
Filing date	Oct 27, 2014
Priority date	Nov 26, 2008
Publication date	Nov 1, 2016
Grant date	Nov 1, 2016

Abstract

Device, system, and method of liveness detection using voice biometrics. For example, a method comprises: generating a first matching score based on a comparison between: (a) a voice-print from a first text-dependent audio sample received at an enrollment stage, and (b) a second text-dependent audio sample received at an authentication stage; generating a second matching score based on a text-independent audio sample; and generating a liveness score by taking into account at least the first matching score and the second matching score.

First claim

What is claimed is:

1. An apparatus comprising:
at least one machine-readable medium storing a plurality of voice-prints corresponding to voice characteristics of respective enrolled users; and
at least one processor programmed to perform:
providing a first prompt to obtain a text-dependent audio sample from a user at an evaluation stage;
providing a second prompt to obtain a text-independent audio sample from the user at the evaluation stage;
and
comparing a voice print of the text-dependent audio sample and the text-independent audio sample;
making an authentication decision about the user based, at least in part, on results of: a comparison between the text-dependent audio sample and a voice print from an enrollment audio sample received at an enrollment stage and the comparison between the voice print of the text-dependent audio sample and the text-independent audio sample.

2. The apparatus of claim 1 , wherein the at least one processor is programmed to generate an utterance validation score based, at least in part, on the text-independent audio sample received at the evaluation stage.

3. The apparatus of claim 2 , wherein generating the utterance validation score comprises:
performing automatic speech recognition on the text-independent audio sample received at the evaluation stage.

4. The apparatus of claim 1 , wherein the at least one processor is further programmed to perform:
generating a first interim score based on a comparison between the text-independent audio sample received at the evaluation stage, and a text-independent voice-print of the text-dependent audio sample received at the evaluation stage;
generating a second interim score based on a comparison between the text-dependent audio sample received at the evaluation stage, and a text-independent voice-print of the text-independent audio sample received at the evaluation stage; and
generating a matching score based, at least in part, on the first interim score and the second interim score.

5. The apparatus of claim 1 , wherein the enrollment audio received at the enrollment stage comprises speech of one or more phrases, and wherein providing the first prompt comprises prompting the user to repeat at least one of the one or more phrases in the evaluation stage.

6. The apparatus of claim 5 , wherein providing the second prompt comprises prompting the user to utter a phrase, in the evaluation stage, different from the one or more phrases included in the enrollment audio received at the enrollment stage.

7. An apparatus comprising:
at least one processor programmed to perform:
providing a first prompt to obtain a text-dependent audio sample from a user at an evaluation stage;
providing a second prompt to obtain a text-independent audio sample from the user at the evaluation stage; and
making an authentication decision about the user based, at least in part, on results of: a comparison between characteristics of the text-dependent audio sample and an enrollment audio sample received at an enrollment stage and a comparison between characteristics of the text-dependent audio sample and the text-independent audio sample.

8. The apparatus of claim 7 , wherein the at least one processor is programmed to generate an utterance validation score based, at least in part, on the text-independent audio sample received at the evaluation stage.

9. The apparatus of claim 8 , wherein generating the utterance validation score comprises:
performing automatic speech recognition on the text-independent audio sample received at the evaluation stage.

10. The apparatus of claim 7 , wherein the at least one processor is further programmed to perform:
comparing the characteristics of the text-dependent audio sample received at the evaluation stage and the text-independent audio sample received at the evaluation stage.

11. The apparatus of claim 7 , wherein the at least one processor is further programmed to perform:
comparing the characteristics of the text-dependent audio sample and the enrollment audio sample received at the enrollment stage.

12. The apparatus of claim 7 , wherein the enrollment audio received at the enrollment stage comprises speech of one or more phrases, and wherein providing the first prompt comprises prompting the user to repeat at least one of the one or more phrases in the evaluation stage.

13. The apparatus of claim 12 , wherein providing the second prompt comprises prompting the user to utter a phrase, in the evaluation stage, different from the one or more phrases included in the enrollment audio received at the enrollment stage.

14. An apparatus comprising:
at least one machine-readable medium storing a plurality of voice-prints corresponding to voice characteristics of respective enrolled users; and
at least one processor programmed to perform:
providing a first prompt to obtain a text-dependent audio sample from a user at an evaluation stage;
providing a second prompt to obtain a text-independent audio sample from the user at the evaluation stage; and
making an authentication decision about the user based, at least in part, on results of a comparison between characteristics of the text-dependent audio sample and a voice print of an enrollment audio sample received at an enrollment stage and a comparison between a voice print of the text-dependent audio sample and characteristics of the text-independent audio sample.

15. The apparatus of claim 14 , wherein the at least one processor is programmed to generate an utterance validation score based, at least in part, on the text-independent audio sample received at the evaluation stage.

16. The apparatus of claim 15 , wherein generating the utterance validation score comprises:
performing automatic speech recognition on the text-independent audio sample received at the evaluation stage.

17. The apparatus of claim 14 , wherein the at least one processor is further programmed to perform:
comparing the voice print of the text-dependent audio sample and the characteristics of the text-independent audio sample.

18. The apparatus of claim 14 , wherein the at least one processor is further programmed to perform:
comparing the characteristics of the text-dependent audio sample and the voice print of the enrollment audio sample received at the enrollment stage.

19. The apparatus of claim 14 , wherein the enrollment audio received at the enrollment stage comprises speech of one or more phrases, and wherein providing the first prompt comprises prompting the user to repeat at least one of the one or more phrases in the evaluation stage.

20. The apparatus of claim 19 , wherein providing the second prompt comprises prompting the user to utter a phrase, in the evaluation stage, different from the one or more phrases included in the enrollment audio received at the enrollment stage.

Assignees

• Nuance Communications Inc

Inventors

• Aley-Raz Almog
• Krause Nir Moshe
• Salmon Michael Itzhak
• Gazit Ran Yehoshua

Classifications

• G10L17/10

  Multimodal systems, i.e. based on the integration of multiple recognition engines or fusion of expert systems · CPC title

• G10L17/24 Primary

  the user being prompted to utter a password or a predefined phrase · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title