SYSTEM AND METHOD FOR LOW OVERHEAD VOICE AUTHENTICATION

• US 20110112830A1
• Filed: 11/10/2009
• Published: 05/12/2011
• Est. Priority Date: 11/10/2009
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Adibi, Sasan
• Granted Patent: US 8,326,625 B2
• Time in Patent Office: Days
• US Class Current: 704/211
• 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

Abstract

A system and method are provided to authenticate a voice in a frequency domain. A voice in the time domain is transformed to a signal in the frequency domain. The first harmonic is set to a predetermined frequency and the other harmonic components are equalized. Similarly, the amplitude of the first harmonic is set to a predetermined amplitude, and the harmonic components are also equalized. The voice signal is then filtered. The amplitudes of each of the harmonic components are then digitized into bits to form at least part of a voice ID. In another system and method, a voice is authenticated in a time domain. The initial rise time, initial fall time, second rise time, second fall time and final oscillation time are digitized into bits to form at least part of a voice ID. The voice IDs are used to authenticate a user'"'"'s voice.

Claims

1. A method of generating a voice identification in a time domain comprising:

identifying in a voice signal an initial rise time portion, an initial fall time portion, a second rise time portion, a second fall time portion and a final oscillation time portion, said time portions forming a period of said voice signal;

measuring the time value of each of said time portions;

digitizing the time value of each of said time portions into a first predetermined number of bits; and

,

concatenating said bits to form said voice identification.

2. The method in claim 1 further comprising setting the time value of said period to a predetermined time and adjusting the time value for each of said time portions to fit within said predetermined time while maintaining the relative time value between said time portions, at least before digitizing the time value of each of said time portions.

3. The method claim 1 further comprising measuring the amplitude of a first peak defined by said initial rise time portion and said initial fall time portion, a second peak defined by said initial fall time portion and said second rise time portion, a third peak defined by said second rise time portion and said second fall time portion, and a fourth peak defined by Said second fall time portion and said final oscillation time portion.

4. The method in claim 1 further comprising setting the amplitude of said first peak to a predetermined voltage and adjusting the amplitudes of said second, third and fourth peaks to maintain relative gain to said first peak.

5. The method in claim 1 further comprising digitizing the amplitudes of each of said second, third and fourth peaks into a second predetermined number of bits, said bits concatenated to said voice identification.

6. The method claim 1 wherein said voice signal is recorded from a user uttering at least one of several pre-determined sounds.

7. The method in claim 6 wherein said predetermined sounds includes any one of “

oh”

, “

aa”

, “

eh”

or “

ee”

, or combinations thereof.

8. The method in claim 6 wherein said at least one of several predetermined sounds is identified by a third number of bits, said third number of bits concatenated to said voice identification.

9. The method in claim 1 further comprising:

in an initialization process, storing said voice identification;

in an authentication process, an authentication voice signal is used to generate another voice identification; and

, if said voice identification and said other authentication voice identification are equal, then said authentication voice signal is considered authentic.

10. A computer readable medium comprising computer executable instructions for generating a voice identification in a time domain, said computer readable medium comprising instructions for:

identifying in a voice signal an initial rise time portion, an initial fall time portion, a second rise time portion, a second fall time portion and a final oscillation time portion, said time portions forming a period of said voice signal;

measuring the time value of each of said time portions;

digitizing the time value of each of said time portions into a first predetermined number of bits; and

, concatenating said bits to form said voice identification.

11. The computer readable medium in claim 10 further comprising setting the time value of said period to a predetermined time and adjusting the time value for each of said time portions to fit within said predetermined time while maintaining the relative time value between said time portions, at least before digitizing the time value of each of said time portions.

12. The computer readable medium in claim 10 further comprising measuring the amplitude of a first peak defined by said initial rise time portion and said initial fall time portion, a second peak defined by said initial fall time portion and said second rise time portion, a third peak defined by said second rise time portion and said second fall time portion, and a fourth peak defined by said second fall time portion and said final oscillation time portion.

13. The computer readable medium in claim 10 further comprising setting the amplitude of said first peak to a predetermined voltage and adjusting the amplitudes of said second, third and fourth peaks to maintain relative gain to said first peak.

14. The computer readable medium in claim 10 further comprising digitizing the amplitudes of each of said second, third and fourth peaks into a second predetermined number of bits, said bits concatenated to said voice identification.

15. The computer readable medium in claim 10 wherein said voice signal is recorded from a user uttering at least one of several pre-determined sounds.

16. The computer readable medium in claim 15 wherein said predetermined sounds includes any one of “

oh”

, “

aa”

, “

eh”

or “

ee”

, or combinations thereof.

17. The computer readable medium in claim 15 wherein said at least one of several predetermined sounds is identified by a third number of bits, said third number of bits concatenated to said voice identification.

18. The computer readable medium in claim 10 further comprising:

in an initialization process, storing said voice identification;

in an authentication process, an authentication voice signal is used to generate another voice identification; and

, if said voice identification and said other authentication voice identification are equal, then said authentication voice signal is considered authentic.

19. A mobile device for generating a voice identification in a time domain, said mobile device comprising a processor and a memory, said memory includes computer executable instructions for:

identifying in a voice signal an initial rise time portion, an initial fall time portion, a second rise time portion, a second fall time portion and a final oscillation time portion, said time portions forming a period of said voice signal;

measuring the time value of each of said time portions;

digitizing the time value of each of said time portions into a first predetermined number of bits; and

,

concatenating said bits to form said voice identification.