System, device, and method for securing voice authentication and end-to-end speech interaction

• US 9,577,784 B2
• Filed: 08/13/2015
• Issued: 02/21/2017
• Est. Priority Date: 09/28/2012
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Dadu, Saurabh, Rishi, Karthik K., Prakash, Gyan, Poornachandran, Rajesh
• Primary Examiner(s): Vaughan, Michael R
• Assistant Examiner(s): McCoy, Richard
• Application Number:
  US14/826,078
• Publication Number:
  US 20150349913A1
• Time in Patent Office: 558 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/62 Protecting access to data via a platform, e.g. using keys or access control rules
• CPC Class Codes: H04K 1/00 Secret communication

Abstract

A method, device, and system for secure end-to-end audio recognition is disclosed. A client device launches an application that connects with a server. The client device and server exchange cryptographic keys and establish a secure connection and a shared cryptographic key. The server transmits an encrypted audio prompt to the client device. The client device decrypts the encrypted audio prompt and stores the decrypted audio prompt in secure memory inaccessible to the operating system using an audio engine of the client device. The audio engine then retrieves the audio and renders it for the user through the speakers of the client device. The client device captures the user'"'"'s audio response with a microphone and stores the audio response in the secure memory. The stored audio response is encrypted and transmitted to the server.

Claims

1. A computing device for securely transferring audio, the computing device comprising:

a central processing unit;

a system memory that is accessible by the central processing unit;

a secure memory that is inaccessible by the central processing unit;

a speaker to output audio based on received audio data;

an audio co-processor to receive encrypted audio data from an application executed on the computing device; and

a security co-processor to (i) decrypt the encrypted audio data and (ii) store the decrypted audio data in the secure memory;

wherein the audio co-processor is further to retrieve the decrypted audio data from the secure memory and (ii) provide the decrypted audio data to the speaker for output;

wherein access to the decrypted audio data requires access to the secure memory.

2. The computing device of claim 1, wherein the audio co-processor includes the secure memory.

3. The computing device of claim 1, wherein the security co-processor includes the secure memory.

4. The computing device of claim 1, further comprising a microphone to generate audio data based on captured audio;

wherein the audio co-processor is further to (i) receive the audio data generated by the microphone and (ii) store the received audio data in the secure memory; and

wherein the security co-processor is further to (i) retrieve the captured audio data from the secure memory, (ii) encrypt the captured audio data, and (iii) store the encrypted audio data in the system memory.

5. The computing device of claim 4, wherein the encrypted audio data received from the application comprises an audio prompt to a user of the computing device.

6. The computing device of claim 5, wherein the received audio data comprises an audio response of the user to the audio prompt.

7. The computing device of claim 1, further comprising a secure audio render pipeline inaccessible by the central processing unit by which to transfer the decrypted audio data from the secure memory to the speaker, wherein audio data in the secure audio render pipeline is inaccessible by the central processing unit.

8. A method for securely transferring audio on a computing device, the method comprising:

receiving, with an audio co-processor different from a central processing unit of the computing device, encrypted audio data from an application executed on the computing device;

decrypting, by a security co-processor different from the central processing unit, the encrypted audio data;

storing, by the security co-processor, the decrypted audio data in a secure memory inaccessible by the central processing unit;

retrieving, with the audio co-processor of the computing device, the decrypted audio data from the secure memory; and

providing, by the audio co-processor, the decrypted audio data to a speaker of the computing device for output;

wherein access to the decrypted audio data requires access to the secure memory.

9. The method of claim 8, wherein storing the decrypted audio data comprises storing the decrypted audio data in a secure memory of the audio co-processor;

and

wherein retrieving the decrypted audio data from the secure memory comprises retrieving the decrypted audio data from the secure memory of the audio co-processor.

10. The method of claim 8, wherein storing the decrypted audio data comprises storing the decrypted audio data in a secure memory of the security co-processor;

and

wherein retrieving the decrypted audio data from the secure memory comprises retrieving the decrypted audio data from the secure memory of the security co-processor.

11. The method of claim 8, further comprising:

capturing, with the audio co-processor, audio data generated by a microphone;

storing, by the audio co-processor, the captured audio data in the secure memory;

retrieving, with the security co-processor, the captured audio data from the secure memory;

encrypting, by the security co-processor, the retrieved audio data; and

storing the encrypted audio data in a system memory that is accessible by the central processing unit.

12. The method of claim 8, further comprising establishing a secure audio render pipeline inaccessible by the central processing unit by which to transfer the decrypted audio data from the secure memory to the speaker, wherein audio data in the secure audio render pipeline is inaccessible by the central processing unit.

13. A computing device for securely capturing audio, the computing device comprising:

a central processing unit;

a system memory that is accessible by the central processing unit;

a secure memory that is inaccessible by the central processing unit;

a microphone to generate audio data based on captured audio;

an audio co-processor to (i) receive the generated audio data and (ii) store the received audio data in the secure memory; and

a security co-processor to (i) retrieve the stored audio data from the secure memory (ii) encrypt the retrieved audio data and (iii) store the encrypted audio data in the system memory;

wherein access to unencrypted audio data requires access to the secure memory.

14. The computing device of claim 13, wherein the audio co-processor includes the secure memory.

15. The computing device of claim 13, wherein the security co-processor includes the secure memory.

16. The computing device of claim 13, further comprising a secure audio capture pipeline inaccessible by the central processing unit by which to transfer the audio data generated by the microphone from the microphone to the secure memory, wherein audio data in the secure audio capture pipeline is inaccessible by the central processing unit.

17. A method for securely capturing audio on a computing device, the method comprising:

capturing, with an audio co-processor different from a central processing unit of the computing device, audio data generated by a microphone;

storing, by the audio co-processor, the captured audio data in a secure memory inaccessible by the central processing unit;

retrieving, with a security co-processor different from the central processing unit, the stored audio data from the secure memory;

encrypting, by the security co-processor, the retrieved audio data; and

storing the encrypted audio data in a system memory that is accessible by the central processing unit;

wherein access to unencrypted audio data requires access to the secure memory.

18. The method of claim 17, wherein storing the captured audio data in the secure memory comprises storing the captured audio data in a secure memory of the audio co-processor;

and

wherein retrieving the captured audio data from the secure memory comprises retrieving the captured audio data from the secure memory of the audio co-processor.

19. The method of claim 17, wherein storing the captured audio data in the secure memory comprises storing the captured audio data in a secure memory of the security co-processor;

and

wherein retrieving the captured audio data from the secure memory comprises retrieving the captured audio data from the secure memory of the security co-processor.

20. The method of claim 17, further comprising establishing a secure audio capture pipeline inaccessible by the central processing unit by which to transfer the audio data generated by the microphone from the microphone to the secure memory, wherein audio data in the secure audio capture pipeline is inaccessible by the central processing unit.