# US 2025/0149030 A1 · Method for operating a hearing aid system and hearing aid system

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

- Number: US 2025/0149030 A1
- Document ID: US20250149030A1
- Status: Published application
- Kind: A1
- Application number: 18/939,940
- Filed: 2024-11-07
- Published: 2025-05-08
- Earliest claimed: 2023-11-07
- Assignees: Sivantos Pte. Ltd.
- Applicants: Sivantos Pte. Ltd.
- Inventors: Julius KRIEG
- Web page: https://patentgrep.com/patent/US20250149030A1

## CPC

- G10L 15/183: using context dependencies, e.g. language models
- G06F 3/015: {Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection}
- G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- H04R 25/505: {using digital signal processing}
- H04R 25/554: {using a wireless connection, e.g. between microphone and amplifier or using Tcoils}
- H04R 2225/39: Aspects relating to automatic logging of sound environment parameters and the performance of the hearing aid during use, e.g. histogram logging, or of user selected programs or settings in the hearing aid, e.g. usage logging
- H04R 2225/41: Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
- H04R 2225/43: Signal processing in hearing aids to enhance the speech intelligibility
- H04R 2225/55: Communication between hearing aids and external devices via a network for data exchange
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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 method for operating hearing aid systems includes a receiving unit receiving and converting speech information into a speech signal, a speech recognition unit converting a speech signal into a text signal, a prompt unit generating a context-dependent prompt for a natural language processing unit, a triggering unit triggering the prompt unit as required and specifying a stored context, an evaluation unit evaluating a prompt by a natural language processing unit and generating an output signal, and an output unit outputting an output signal to a user. Upon triggering the triggering unit, at least one section of the speech signal is converted into a text signal by the speech recognition unit, a prompt is generated for the natural language processing unit by the stored context and text signal, the natural language processing unit generates an output signal based on the prompt, and the output unit outputs the output signal.

## Claims

### Claim 1

A method for operating a hearing aid system, the method comprising:
using a receiving unit for receiving speech information and converting the speech information into a speech signal;
using a speech recognition unit for converting the speech signal into a text signal;
using a prompt unit for generating a context-dependent prompt for a natural language processing unit;
using a triggering unit for triggering the prompt unit as required and specifying a stored context;
using an evaluation unit for evaluating the prompt by using the natural language processing unit and for generating an output signal;
using an output unit for outputting the output signal to a user; and
upon triggering the triggering unit:
a) converting at least one section of the speech signal into a text signal by using the speech recognition unit,
b) generating the prompt for the natural language processing unit by using the stored context and the text signal,
c) using the natural language processing unit to generate the output signal based on the prompt, and
d) using the output unit to output the output signal.

### Claim 2 (depends on 1)

The method according to claim 1, which further comprises triggering the triggering unit by using at least two different trigger types each being linked to a different, stored, context, and generating the prompt for the natural language processing unit depending on the trigger type.

### Claim 3 (depends on 2)

The method according to claim 2, which further comprises using a gesture of a hearing aid system user as at least one of the trigger types.

### Claim 4 (depends on 1)

The method according to claim 1, which further comprises generating a section of the speech signal or a combination of at least two sections of the speech signal as the output signal.

### Claim 5 (depends on 1)

The method according to claim 1, which further comprises storing a hearing profile for a user of the hearing aid system, and generating the prompt in dependence on the hearing profile.

### Claim 6 (depends on 1)

The method according to claim 1, which further comprises using a physiological sensor for acquiring information about a bodily state of a user of the hearing system and outputting sensor data, and at least one of:
adjusting the output signal by using the sensor data from the physiological sensor, or
comparing the sensor data from the physiological sensor with a stored threshold value, and triggering the triggering unit upon reaching or exceeding the threshold value.

### Claim 7 (depends on 1)

The method according to claim 1, which further comprises storing and substantially continuously updating the speech signal over a predetermined period of time during operation until the triggering unit is triggered, and using the stored speech signal by the speech recognition unit.

### Claim 8 (depends on 1)

The method according to claim 1, which further comprises paraphrasing at least one section of the text signal for the output signal in a course of natural language processing.

### Claim 9 (depends on 1)

The method according to claim 1, which further comprises acoustically outputting the output signal to the user.

### Claim 10

A hearing aid system, comprising:
a receiving unit for receiving speech information and converting the speech information into a speech signal;
a speech recognition unit for converting the speech signal into a text signal;
a prompt unit for generating a context-dependent prompt;
a natural language processing unit for receiving the context-dependent prompt;
a triggering unit for triggering said prompt unit as required and specifying a stored context;
an evaluation unit for evaluating the prompt by using said natural language processing unit and for generating an output signal; and
an output unit for outputting the output signal to a user.
