# US 2023/0053811 A1 · Methods and systems for voice recognition in autonomous flight of an electric aircraft

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

- Number: US 2023/0053811 A1
- Document ID: US20230053811A1
- Status: Published application
- Kind: A1
- Application number: 17/721,477
- Filed: 2022-04-15
- Published: 2023-02-23
- Earliest claimed: 2021-08-20
- Assignees: Beta Air, LLC
- Applicants: Beta Air, LLC
- Inventors: Alexander Hoekje List; Vincent Moeykens
- Web page: https://patentgrep.com/patent/US20230053811A1

## CPC

- G06F 16/355: Creation or modification of classes or clusters
- G08G 5/34: for flight plan modification
- G06F 16/61: Indexing; Data structures therefor; Storage structures
- G06F 16/63: Querying
- G06F 16/65: Clustering; Classification
- G06F 16/685: {using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00)}
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G08G 5/21: located onboard the aircraft
- G08G 5/26: Transmission of traffic-related information between aircraft and ground stations
- G08G 5/265: for managing air traffic control [ATC] clearance
- G08G 5/55: for a single aircraft
- G08G 5/57: for unmanned aircraft
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G10L 2015/223: {Execution procedure of a spoken command}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system for voice recognition in autonomous flight of an electric aircraft that includes a computing device communicatively connected to the electric aircraft configured to receive at least a voice datum from a remote device, wherein the voice datum is configured to include at least an expression datum, generate, using a first machine-learning process, a transcription datum as a function of the at least a voice datum, extract at least a query as a function of the transcription datum, generate, using a second machine-learning process, a communication output as a function of the at least a query, and adjust a flight plan as a function of the communication output.

## Claims

### Claim 1

A system for voice recognition in autonomous flight of an electric aircraft, the system comprising:
a computing device communicatively connected to the electric aircraft, the computing device is configured to:
receive at least a voice datum from a remote device, wherein the voice datum is configured to include at least an expression datum;
generate a communication output as a function of the at least an expression datum; and
adjust a flight plan as a function of the communication output.

### Claim 2 (depends on 1)

The system of claim 1, wherein the computing device is further configured to transmit an adjustment notification to an interface device as a function of adjusting the flight plan.

### Claim 3 (depends on 2)

The system of claim 2, wherein the system is further comprises the interface device, wherein the interface device is configured to display the adjustment notification to a user.

### Claim 4 (depends on 1)

The system of claim 1, wherein the computing device is further configured to:
generate a transcription datum wherein generating a transcription datum comprises a machine learning process configured to generate a transcription datum as a function of the at least a voice datum; and
transmit the transcription datum to the interface device.

### Claim 5 (depends on 4)

The system of claim 4, wherein generating the transcription datum further comprises:
selecting a correlated dataset containing a plurality of data entries wherein each dataset contains at least a datum of expression data and at least a first correlated content datum as a function of the at least a voice datum; and
generating, at a clustering unsupervised machine-learning model, a transcription datum as a function of the at least a voice datum and the correlated dataset.

### Claim 6 (depends on 4)

The system of claim 4, wherein the computing device is further configured to extract at least a query as a function of the transcription datum, wherein the at least a.

### Claim 7 (depends on 1)

The system of claim 1, wherein generating the communication output further comprises:
receiving, at a supervised machine-learning model, a first training set as a function of the at least a voice datum and at least a query; and
generating, at a supervised machine-learning model, a communication output as a function of relating the at least a query to at least a textual output.

### Claim 8 (depends on 1)

The system of claim 1, wherein the computing device is further configured to:
generate a response datum as a function of the communication output; and
transmit the response datum to the remote device.

### Claim 9 (depends on 1)

The system of claim 1, wherein receiving the at least a voice datum further comprises storing the voice datum, as a dataset, in a data storage system.

### Claim 10 (depends on 9)

The system of claim 9, wherein the computing device is further configured to train a machine learning process as a function of the voice datum dataset.

### Claim 11

A method for voice recognition in autonomous flight of an electric aircraft, the method comprising:
receiving, at a computing device, at least a voice datum from a remote device, wherein the voice datum is configured to include at least an expression datum;
generating, at the computing device, a communication output as a function of the at least an expression datum; and
adjusting, at the computing device, a flight plan as a function of the communication output.

### Claim 12 (depends on 11)

The method of claim 11, wherein the computing device is further configured to transmit an adjustment notification to an interface device as a function of adjusting the flight plan.

### Claim 13 (depends on 12)

The method of claim 12, wherein the method is further comprises an interface device, wherein the interface device is configured to display the adjustment notification to a user.

### Claim 14 (depends on 11)

The method of claim 11, wherein the computing device is further configured to:
generate a transcription datum wherein the generating a transcription datum comprises a machine learning process configured to generate a transcription datum as a function of the at least a voice datum; and
transmit the transcription datum to an interface device.

### Claim 15 (depends on 14)

The method of claim 14, wherein generating the transcription datum further comprises:
selecting a correlated dataset containing a plurality of data entries wherein each dataset contains at least a datum of expression data and at least a first correlated content datum as a function of the at least a voice datum; and
generating, at a clustering unsupervised machine-learning model, a transcription datum as a function of the at least a voice datum and the correlated dataset.

### Claim 16 (depends on 14)

The method of claim 14, further comprising extracting at least a query as a function of the transcription datum, wherein the at least a query is extracted at a language processing module.

### Claim 17 (depends on 11)

The method of claim 11, wherein generating the communication output further comprises:
receiving, at a supervised machine-learning model, a first training set as a function of the at least a voice datum and at least a query; and
generating, at a supervised machine-learning model, a communication output as a function of relating the at least a query to at least a textual output.

### Claim 18 (depends on 11)

The method of claim 11, wherein the computing device is further configured to:
generate a response datum as a function of the communication output; and
transmit the response datum to the remote device.

### Claim 19 (depends on 11)

The method of claim 11, wherein receiving the at least a voice datum further comprises storing the voice datum, as a dataset, in a data storage system.

### Claim 20 (depends on 19)

The method of claim 19, wherein the method further comprises training a machine learning process as a function of the voice datum dataset.
