# US 2021/0174818 A1 · Ear-worn electronic device incorporating annoyance model driven selective active noise control

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0174818 A1
- Document ID: US20210174818A1
- Status: Published application
- Kind: A1
- Application number: 17/125,566
- Filed: 2020-12-17
- Published: 2021-06-10
- Earliest claimed: 2017-10-30
- Assignees: Starkey Laboratories, Inc.
- Applicants: Starkey Laboratories, Inc.
- Inventors: Ritwik Giri; Karim Helwani; Tao Zhang
- Web page: https://patentgrep.com/patent/US20210174818A1

## CPC

- G10L 21/0216: characterised by the method used for estimating noise
- 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
- G10L 21/0208: Noise filtering
- H04R 1/1083: {Reduction of ambient noise (active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06)}
- H04R 3/002: {Damping circuit arrangements for transducers, e.g. motional feedback circuits}
- H04R 5/04: Circuit arrangements, {e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments (combinations of amplifiers H03F3/68; stereophonic systems H04S)}
- H04R 25/505: {using digital signal processing}
- G10L 2021/02087: {the noise being separate speech, e.g. cocktail party}
- G10L 2021/02163: {Only one microphone}
- H04R 5/033: Headphones for stereophonic communication {(details thereof, e.g. relating to batteries, cables or control elements H04R1/10)}
- H04R 2460/01: Hearing devices using active noise cancellation
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A system comprises an ear-worn electronic device configured to be worn by a wearer. The ear-worn electronic device comprises a processor and memory coupled to the processor. The memory is configured to store an annoying sound dictionary representative of a plurality of annoying sounds pre-identified by the wearer. A microphone is coupled to the processor and configured to monitor an acoustic environment of the wearer. A speaker or a receiver is coupled to the processor. The processor is configured to identify different background noises present in the acoustic environment, determine which of the background noises correspond to one or more of the plurality of annoying sounds, and attenuate the one or more annoying sounds in an output signal provided to the speaker or receiver.

## Claims

### Claim 1

(canceled)

### Claim 2

An ear-worn electronic device, comprising:
a housing configured to be supported by, at, in or on an ear of a wearer and to contain or support:
a microphone configured to monitor an acoustic environment of the wearer;
an acoustic transducer; and
an active noise control (ANC) system operatively coupled to a processor, the microphone, and the acoustic transducer, the ANC system configured to be driven by an annoyance model and to selectively attenuate one or more of a plurality of annoying sounds pre-identified by the wearer.

### Claim 3 (depends on 2)

The device of claim 2, wherein the ANC system is configured to be driven by a phychoacoustic annoyance model.

### Claim 4 (depends on 2)

The device of claim 2, wherein the ANC system is configured to selectively attenuate one or more of the plurality of annoying sounds by a degree of attenuation pre-identified by the wearer.

### Claim 5 (depends on 2)

The device of claim 2, wherein the ANC system is configured to apply attenuation to specified subbands of one or more of the plurality of annoying sounds.

### Claim 6 (depends on 2)

The device of claim 2, wherein the ANC system is configured to identify or fingerprint background noises present in the wearer's acoustic environment based on noise fingerprints learned during an offline training stage of the ANC system.

### Claim 7 (depends on 2)

The device of claim 2, wherein the ANC system is configured to operate during an offline training stage and during one or both of an online testing stage and an online actual-use stage.

### Claim 8 (depends on 7)

The device of claim 7, wherein the ANC system is configured to identify or fingerprint the plurality of annoying sounds using a Non-negative Matrix Factorization (NMF) process during the offline training stage and during one or both of the online testing stage and the online actual-use stage.

### Claim 9 (depends on 2)

The device of claim 2, wherein the ANC system is configured to, during an offline training stage:
identify or fingerprint different annoying sounds;
compute an annoyance score for each annoying sound based at least in part on wearer input; and
assign the annoyance score to each of the annoying sounds.

### Claim 10 (depends on 9)

The device of claim 9, wherein the ANC system is configured to adjust the annoyance score of one or more of the annoying sounds in response to a wearer input.

### Claim 11 (depends on 2)

The device of claim 2, wherein the ANC system is configured to:
identify background sounds present in the wearer's acoustic environment; and
assign a soft membership score to each of the identified background sounds.

### Claim 12 (depends on 11)

The device of claim 11, wherein:
the ANC system comprises a Kalman filter-based noise canceler; and
the soft membership scores and the annoyance scores are used by the ANC system to inform the Kalman filter-based noise canceler to cancel the annoying sounds, but pass through all other sounds.

### Claim 13

A method implemented by an ear-worn electronic device comprising a housing configured to be worn at, in or on an ear of a wearer, the method comprising:
monitoring an acoustic environment of the wearer using a microphone;
identifying, by an active noise control (ANC) system driven by an annoyance model, different annoying sounds pre-identified by the wearer that are present in the acoustic environment; and
selectively attenuating, by the ANC system, one or more of the different annoying sounds pre-identified by the wearer.

### Claim 14 (depends on 13)

The method of claim 13, wherein the ANC system is driven by a phychoacoustic annoyance model.

### Claim 15 (depends on 13)

The method of claim 13, wherein the ANC system selectively attenuates one or more of the different annoying sounds by a degree of attenuation pre-identified by the wearer.

### Claim 16 (depends on 13)

The method of claim 13, wherein the ANC system applies attenuation to specified subbands of one or more of the different annoying sounds.

### Claim 17 (depends on 13)

The method of claim 13, wherein the ANC system identifies or fingerprints background noises present in the wearer's acoustic environment based on noise fingerprints learned during an offline training stage of the ANC system.

### Claim 18 (depends on 13)

The method of claim 13, wherein the ANC system operates during an offline training stage and during one or both of an online testing stage and an online actual-use stage.

### Claim 19 (depends on 18)

The method of claim 18, wherein the ANC system identifies or fingerprints the different annoying sounds using a Non-negative Matrix Factorization (NMF) process during the offline training stage and during one or both of the online testing stage and the online actual-use stage.

### Claim 20 (depends on 13)

The method of claim 13, wherein the ANC system, during an offline training stage:
identifies or fingerprints the different annoying sounds;
computes an annoyance score for each annoying sound based at least in part on wearer input; and
assigns the annoyance score to each of the annoying sounds.

### Claim 21 (depends on 20)

The method of claim 20, wherein the ANC system adjusts the annoyance score of one or more of the different annoying sounds in response to a wearer input.

### Claim 22 (depends on 13)

The method of claim 13, wherein the ANC system:
identifies background sounds present in the wearer's acoustic environment; and
assigns a soft membership score to each of the identified background sounds.

### Claim 23 (depends on 23)

The method of claim 23, wherein:
the ANC system comprises a Kalman filter-based noise canceler; and
the soft membership scores and the annoyance scores are used by the ANC system to inform the Kalman filter-based noise canceler to cancel the different annoying sounds, but pass through all other sounds.

### Claim 24

An ear-worn electronic device, comprising:
a housing configured to be supported by, at, in or on an ear of a wearer and to contain or support:
a microphone configured to monitor an acoustic environment of the wearer;
an acoustic transducer; and
an active noise control (ANC) system operatively coupled to a processor, the microphone, and the acoustic transducer, the ANC system configured to be driven by an annoyance model and to:
selectively attenuate one or more of a plurality of annoying sounds pre-identified by the wearer by a degree of attenuation pre-identified by the wearer; and
apply attenuation to specified subbands of one or more of the plurality of annoying sounds.

### Claim 25 (depends on 24)

The device of claim 24, wherein the ANC system is configured to be driven by a phychoacoustic annoyance model.
