Noise event detection and characterization

Patent metadata

Field	Value
Publication number	US-12211516-B2
Application number	US-202017906011-A
Country	US
Kind code	B2
Filing date	Mar 10, 2020
Priority date	Mar 10, 2020
Publication date	Jan 28, 2025
Grant date	Jan 28, 2025

Abstract

A method characterizes a noise event, and includes locating microphones in an environment and generating a training event at a location in the environment as a reference for a noise event. A sound sample is recorded at each microphone and phase differences between the sound samples are used to establish a noise event signature for an event at that location. A noise event may subsequently be identified by taking sound samples from the microphones associated with the noise event and using phase differences between them to identify the noise event by matching against noise event signatures.

First claim

The invention claimed is:

1. A method of characterising a noise event, comprising:
locating a plurality of microphones in an environment;
generating a training event at a location in the environment as a reference for a noise event;
recording a sound sample at each of the plurality of microphones;
determining phase differences between the sound samples of different microphones from the plurality of microphones; and,
establishing a reference noise event signature for the noise event at the location from the determined phase differences between sounds associated with the training event at different microphones of the plurality of microphones.

2. The method of claim 1 , wherein the event is an event of a predetermined type.

3. The method of claim 1 , further comprising determining whether the phase differences between the sound samples meet a quality threshold for establishing the noise event signature, and generating a further training event at the location if the phase differences do not meet the quality threshold, and establishing the noise event signature from the training event and the further training event.

4. The method of claim 3 , wherein determining whether the phase differences between the sound samples meet a quality threshold comprises determining whether they meet a predetermined threshold for recognition of test events as corresponding to the noise event.

5. The method of claim 1 , wherein determining phase differences comprises first transforming the sound samples into the frequency domain.

6. The method of claim 5 , wherein a Fast Fourier Transform is used to transform sound samples into the frequency domain.

7. The method of claim 5 , wherein determining phase differences comprises establishing a feature vector comprising phase differences between a pair of microphones in said plurality of microphones across a plurality of frequency bins.

8. The method of claim 7 , wherein determining phase differences comprises a feature matrix resolvable into a plurality of said feature vectors each involving phase differences between different pairs of microphones of said plurality of microphones.

9. A method of identifying a noise event, wherein noise events have been characterised by reference noise event signatures from phase differences between determined sounds associated with the noise event type at different microphones of a plurality of microphones located in an environment, the method comprising:
identifying a sound sample at different microphones of the plurality of microphones as being associated with the noise event;
determining phase differences between the sound samples at the different microphones of the plurality of microphones to establish a signature for the noise event; and,
matching the signature of the noise event against the previously characterised reference noise event signatures for noise event types to identify the noise event.

10. The method of claim 9 , wherein the previously characterised signatures indicate a noise event location.

11. The method of claim 8 , wherein the previously characterised reference noise event signatures indicate a noise event type.

12. The method of claim 9 , wherein determining phase differences comprises first transforming the sound samples into the frequency domain.

13. The method of claim 12 , wherein a Fast Fourier Transform is used to transform sound samples into the frequency domain.

14. The method of claim 9 , wherein at least some of the previously characterised signatures comprise a feature vector comprising phase differences between a pair of microphones in said plurality of microphones across a plurality of frequency bins.

15. The method of claim 14 , wherein at least some of the previously characterised signatures comprise a feature matrix resolvable into a plurality of said feature vectors each involving phase differences between different pairs of microphones of said plurality of microphones.

16. The method of claim 14 , wherein matching comprises determining the microphones of the plurality for which the noise event has been identified, determining parts of a previously characterised reference noise event signature that relate to the microphones of the plurality for which the noise event has been identified, and only using those parts of the previously characterised reference noise event signature in matching.

17. A computing system adapted to identify noise events in an environment, wherein the computing system is configured to receive sound samples from each of a plurality of microphones located in the environment, wherein the computing system is adapted to establish a plurality of reference noise event signatures from determined phase differences between sounds associated with the noise event at different microphones of the plurality of microphones, and is further adapted to determine signals corresponding to a noise event from the plurality of microphones and to identify the noise event by matching the signals from the plurality of microphones against the plurality of reference noise event signatures.

18. The computing system of claim 17 , wherein the computing system is adapted to establish the plurality of reference noise event signatures by a method comprising the steps of:
locating a plurality of microphones in an environment;
generating a training event at a location in the environment as a reference for a noise event;
recording a sound sample at each of the plurality of microphones;
determining phase differences between the sound samples of different microphones from the plurality of microphones; and,
establishing a reference noise event signature for the noise event at the location from the determined phase differences between sounds associated with the training event at different microphones of the plurality of microphones.

19. The computing system of claim 17 , wherein the computing system is adapted to identify the detected noise event by a method wherein noise events have been characterised by phase differences between sound samples associated with the noise event type at different microphones of a plurality of microphones located in an environment, the method comprising:
identifying a sound sample at different microphones of the plurality of microphones as being associated with the noise event;
determining phase differences between the sound samples at the different microphones of the plurality of microphones to establish a signature for the noise event; and,
matching the signature of the noise event against previously characterised reference noise event signatures for noise event types to identify the noise event.

20. A power management system, comprising a control system receiving event data from a plurality of local computing systems and one or more local computing systems being computing systems as claimed in claim 16 and adapted to report identified noise events to the control system.

Assignees

• Eaton Intelligent Power Ltd

Inventors

• Cahill Niall
• Van De Belt Johannes
• Nolan Keith

Classifications

• H04R1/406

  microphones · CPC title

• G10K11/346

  using phase variation · CPC title

• G10L25/51 Primary

  for comparison or discrimination · CPC title

• G01H3/125 Primary

  for representing acoustic field distribution (using optical means G01H9/002; sonar systems for imaging G01S7/56, G01S15/89; acoustic holography G03H3/00) · CPC title