SOUND VERIFICATION SYSTEM USING TEMPLATES

• US 20110320201A1
• Filed: 06/02/2011
• Published: 12/29/2011
• Est. Priority Date: 06/24/2010
• Status: Abandoned Application

• Current Assignee: John D. Kaufman
• Original Assignee: John D. Kaufman
• Inventors: KAUFMAN, John D.
• Application Number:
  US13/152,149
• Publication Number:
  US 20110320201A1
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 17/04 Training, enrolment or model building

Abstract

An audio signal verification system is presented for verifying the sound is from a predetermined source. Various methods for analyzing the sound are presented and the various methods may be combined to vary degrees to determine an appropriate correlation with a predefined pattern. Moreover a confidence level or other indication may be used to indicate the determination was successful. The sound may be reduced to templates with varying degrees of richness. Also different templates may be created using the same sound source and different sounds from the same source may be aggregated to form a single template. Comparisons may be made comparing a sound or a template derived from that sound with stored sounds or templates derived from that stored sound. Moreover comparisons can be made using templates of different richness to achieve confidence levels and confidence levels may be represented based on the results of the comparisons.

Claims

1. A method comprising:

receiving, at a server, first data, said first data including information representing an audio signal;

creating a template in response to a portion of the first data, and

storing the template in a memory.

2. The methods of claim 1 wherein the structured data is digitized speech.

3. The method of claim 1 wherein the first data includes at least one of a location, a user, a time, a device or a unique identifier.

4. The method of claim 1 wherein the template is an array representing spectral components of at least a portion of the audio signal.

5. The method of claim 4 wherein the spectral components comprise the substantially predominate frequencies of the audio signal.

6. The method of claim 1 wherein the template includes relationship information, said relationship information relating a first portion of the audio signal to a second portion of the audio signal.

7. The method of claim 1 further including:

processing the first data to eliminate noise.

8. The methods of claim 1 further including:

receiving second data, said second data including information associated with a second audio signal.

9. The method of claim 8 wherein the template is modified in response to the second audio signal

10. The method of claim 9 wherein said modification includes either adding a portion of the second data to the first data or subtracting a portion of the second data from the first data.

11. A method comprising

receiving a first template, said first template including an array of numbers characterizing at least a portion of an audio signal, said array further including identification information, and

storing said template in non-transitory storage media.

12. The method of claim 11 further including:

receiving a second template, said second template including an array of numbers characterizing at least a portion of an audio signal;

comparing the first template to the second template, and

transmitting a parameter responsive to said comparing.

13. The method of claim 12 wherein the parameter is a correlation indication.

14. The method of claim 12 further including:

receiving a minimum correlation value,

wherein the parameter indicates the comparing exceeded the minimal correlation value.

15. The method of claim 11 further including:

receiving a plurality of templates, each template of said plurality of templates including an array of numbers characterizing at least a portion of an said audio signal, and each template of said plurality of templates characterized by a different richness.

16. The method of claim 15 further including:

receiving a second template, said second template including an array of numbers characterizing at least a portion of an audio signal;

comparing at least one of the plurality of templates to the first template, and

transmitting a parameter responsive to said comparing.

17. The method of claim 16 wherein the parameter is a correlation indication.

18. The method of claim 16 further including:

receiving a minimum correlation value,

wherein the parameter indicates the comparing exceeded the minimal correlation value.

19. A method comprising:

receiving an audio signal from a sound transducer, and

creating a plurality of templates from said audio signal, each template characterized by a different richness.

20. The method of claim 19 further including:

receiving identification information associated with the audio signal and storing the template and identification information as non-transitory structured data.