# US 2022/0284918 A1 · Method and apparatus for tiredness detection

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

- Number: US 2022/0284918 A1
- Document ID: US20220284918A1
- Status: Published application
- Kind: A1
- Application number: 17/673,353
- Filed: 2022-02-16
- Published: 2022-09-08
- Earliest claimed: 2021-03-05
- Assignees: Dr. Ing. h.c. F. Porsche Aktiengesellschaft
- Applicants: Dr. Ing. h.c. F. Porsche Aktiengesellschaft
- Inventors: Michael Grimm
- Web page: https://patentgrep.com/patent/US20220284918A1

## CPC

- A61B 5/18: for vehicle drivers {or machine operators}
- G10L 25/51: for comparison or discrimination
- A61B 5/168: {Evaluating attention deficit, hyperactivity}
- A61B 5/6893: {Cars}
- A61B 5/7203: {for noise prevention, reduction or removal}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- G08B 21/06: indicating a condition of sleep, e.g. anti-dozing alarms
- G10L 21/0208: Noise filtering
- H04R 1/406: {microphones}
- H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)}
- A61B 5/08: Measuring devices for evaluating the respiratory organs
- A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes}
- A61B 2503/22: Motor vehicles operators, e.g. drivers, pilots, captains
- A61B 2562/0204: Acoustic sensors
- G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00)
- H04R 2499/13: Acoustic transducers and sound field adaptation in vehicles
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- 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 and apparatus (100) are provided for detecting tiredness of a vehicle driver. The apparatus (100) is configured to receive a signal from at least one microphone (104), to acquire a time characteristic of yawning actions in the signal, and to use an analysis of the time characteristic to detect or not detect a tiredness of the driver (106) from a frequency of yawning, a yawn intensity and/or a temporal compression between successive yawning actions.

## Claims

### Claim 1

An apparatus (100) for tiredness detection, the apparatus (100) being configured to receive a signal from at least one microphone (104), to acquire a time characteristic of yawning actions in the signal, and to use an analysis of the time characteristic to detect or not detect a tiredness of the driver (106) from a frequency of yawning, a yawn intensity and/or a temporal compression between successive yawning actions.

### Claim 2 (depends on 1)

The apparatus (100) of claim 1, wherein the apparatus (100) is designed to evaluate the signal in the analysis using pattern recognition and/or artificial intelligence.

### Claim 3 (depends on 2)

The apparatus (100) of claim 2, wherein the at least one microphone (104) or the apparatus (100) comprises at least one filter designed to filter the signal in to eliminate sounds other than yawning sounds.

### Claim 4 (depends on 1)

The apparatus (100) of claim 1, wherein the apparatus (100) is designed to analyze the signal by extracting paralinguistic traits, in particular a pitch characteristic, a continuity of a tonal characteristic and/or at least one spectral trait, the apparatus being designed to detect a chronological succession of audible inhalation and tonal exhalation in the time characteristic and to determine a result of the analysis on the basis of the chronological succession.

### Claim 5 (depends on 1)

The apparatus (100) of claim 1, wherein the apparatus (100) is designed to receive a plurality of signals from a plurality of microphones, the signals being filtered using filters associated with the respective microphones (104) and the apparatus performing the analysis using the plurality of signals.

### Claim 6 (depends on 1)

A vehicle (102) comprising the apparatus (100) of claim 1 and at least one microphone (104), the at least one microphone (104) being arranged in an interior of the vehicle (102) and being designed to capture audible sound coming from a driver (106) of the vehicle (102) and to transmit a corresponding signal to the apparatus (100).

### Claim 7

A method for tiredness detection, the method comprising:
receiving a signal from at least one microphone, acquiring a time characteristic of yawning actions in the signal, analyzing the time characteristic to detect or not detect (208) a tiredness of the driver from a frequency of yawning, a yawn intensity and/or a temporal compression between successive yawning actions.

### Claim 8 (depends on 7)

The method of claim 7, wherein the signal is evaluated in the analysis using pattern recognition and/or artificial intelligence.

### Claim 9 (depends on 7)

The method of claim 7, wherein the signal is filtered using a filter in order to eliminate sounds other than yawning sounds.

### Claim 10 (depends on 7)

The method of claim 7, wherein the signal is analyzed by extracting at least one paralinguistic traits selected from the group consisting of a pitch characteristic, a continuity of a tonal characteristic, and/or at least one spectral trait, a chronological succession of audible inhalation and tonal exhalation being detected in the time characteristic and a result of the analysis being determined on the basis of the chronological succession.