SOUND CAPTURING AND IDENTIFYING DEVICES

• US 20150112678A1
• Filed: 12/30/2014
• Published: 04/23/2015
• Est. Priority Date: 12/15/2008
• Status: Active Grant

• Current Assignee: META Platforms Technologies LLC (Meta Platforms, Inc. (f/k/a Facebook, Inc.))
• Original Assignee: Audio Analytic Ltd. (Meta Platforms, Inc. (f/k/a Facebook, Inc.))
• Inventors: BINKS, DOMINIC FRANK JULIAN, KRSTULOVIC, SACHA, MITCHELL, CHRISTOPHER JAMES
• Granted Patent: US 10,586,543 B2
• Time in Patent Office: Days
• US Class Current: 704/236
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

Broadly speaking, embodiments of the present invention provide a device, systems and methods for capturing sounds, generating a sound model (or “sound pack”) for each captured sound, and identifying a detected sound using the sound model(s). Preferably, a single device is used to capture a sound, store sound models, and to identify a detected sound using the stored sound models.

Claims

1. A sound capturing and identifying device, the device comprising:

a microphone coupled to the device to detect a sound;

an interface for a button wherein the button is configured to, when pressed, cause the device to capture the sound;

a memory for storing the captured sound;

a communication means for transmitting the captured sound to a remote analytics system located remote to the device; and

a processor configured to;

store a sound model for the captured sound in the device by;

receiving a message indicating the button has been pressed;

capturing an example sound detected by the microphone;

transmitting the captured example sound to the remote analytics system; and

receiving and storing a sound model from the remote analytics system, wherein the sound model corresponds to the captured example sound and comprises parameters which enable the device to identify a detected sound; and

analyse a detected sound using the device to identify the sound by;

using the stored sound model to identify the detected sound when detected by the microphone.

2. The device as claimed in claim 1 wherein the processor is further configured to analyse a detected sound to identify the sound by:

receiving a sound detected by the microphone; and

comparing the detected sound to one or more stored sound models.

3. The device as claimed in claim 1 wherein the interface for the button comprises a physical button on the device.

4. The device as claimed in claim 1 wherein the interface for the button comprises a virtual button on a user interface.

5. The device as claimed in claim 4 wherein the user interface is provided on the device.

6. The device as claimed in claim 5 wherein:

the sound capturing and identifying device is coupled to a user device; and

the user interface is provided on the user device to control the sound capturing and identifying device.

7. The device as claimed in claim 1 further comprising at least one indicator to indicate the progress of the sound capture.

8. The device as claimed in claim 7 wherein the at least one indicator comprises an LED provided on the sound capturing and identifying device.

9. The device as claimed in claim 7 wherein the at least one indicator is provided on a user interface.

10. The device as claimed in claimed in claim 1 wherein the processor is further configured to:

receive an input from a user to associate an action with the sound model; and

implement the action when the device identifies the sound corresponding to the sound model.

11. The device as claimed in claim 10 wherein the action comprises sending a message to a consumer electronics device upon identification of the sound.

12. The device as claimed in claims 10 wherein the action comprises controlling one or more devices coupled to the sound capturing and identifying device.

13. The device as claimed in claim 1 wherein the processor is further configured to process the captured example sound prior to transmitting the captured example sound to the remote analytics system.

14. The device as claimed in claim 1 wherein the communication means for transmitting the captured example sound to the remote analytics system is a wired or a wireless communication means.

15. The device as claimed in claim 1, further comprising audio analytic software configured to:

analyse a sound detected by the microphone; and

compare the sound data to one or more stored sound models to identify the detected sound.

16. The device as claimed in claim 1 comprising:

a sound capture module configured to capture a sound; and

a sound processing module configured to store a sound model for the captured sound in the device, and analyse a detected sound using the device to identify the sound.

17. The device as claimed in claim 16 wherein the functionalities of the sound capture module and the sound processing module are distributed.

18. The device as claimed in claim 1 wherein the device is a dedicated device for capturing and identifying sounds.

19. The device as claimed in claim 1 wherein the sounds captured and identified by the device exclude speech.

20. A method of capturing and identifying a sound, the method comprising steps to generate a sound model for a recorded sound by:

using a microphone to capture an example sound;

transmitting the captured example sound to an analytics system for analysis; and

receiving and storing a sound model from the analytics system, wherein the sound model corresponds to the captured example sound and comprises parameters which enable the device to identify a detected sound;

the method further comprising steps to analyse a detected sound to identify the sound by;

receiving as an input a sound detected by the microphone; and

comparing the detected sound to the stored sound model.

21. The method of claim 20 further comprising providing a device with access to audio analytic software configured to analyse the sound detected by the microphone.

22. The method of claim 21 wherein the device comprises an interactive software application having access to the audio analytic software, wherein the interactive software application is configured to enable user interaction with the device to generate the sound model for the recorded sound.

23. The method of claim 22 wherein the interactive software application is configured to:

receive an input from a user to associate an action with the generated sound model; and

implement the action when the device identifies the sound corresponding to the sound model.

24. The method of claim 21 wherein the device comprises the analytics system to generate the sound model for the captured sound, and wherein the step of receiving and storing a sound model comprises receiving the sound model from the analytics system in the device.

25. The method of claim 20 wherein the analytics system to generate the sound model for the captured sound is provided in a remote server or a network of remote servers hosted on the Internet, and wherein the step of receiving and storing a sound model comprises receiving the sound model from the remote server.

26. A non-transitory data carrier carrying processor control code which when running on a device causes the device to perform the method of claim 20.

27. A system for generating a sound model, the system comprising:

one or more sound capture/processing modules configured to;

capture an example sound;

store a sound model corresponding to the captured example sound; and

analyse a detected sound using the stored sound model; and

a sound model generating module.

28. The system as claimed in claim 27 further comprising a communication channel through which:

a sound captured by the device is sent from the one or more sound capture and/or processing modules to the sound model generating module for analysis; and

the sound model generated by the sound model generating module is returned to the device.

29. The system as claimed in claim 27 wherein the sound model generating module is provided in a remote server or a network of remote servers hosted on the Internet, and a sound recorded by the device is sent to the remote server or network of remote servers for analysis.

30. The system as claimed in claim 27 wherein the sound model generating module analyses a sound recorded by the device, and generates a sound model comprising a set of parameters which characterise the recorded sound.

31. The system as claimed in claim 27 wherein the one or more sound capture/processing modules is further configured to:

receive as an input a detected sound; and

compare the detected sound to one or more stored sound models to identify the detected sound.

32. The system as claimed in claim 27 wherein the one or more sound capture/processing modules is further configured to:

receive an input from a user to associate an action with a sound model; and

implement the action when the sound is identified as corresponding to the stored sound models.