Voice interface for a vehicle

• US 9,928,833 B2
• Filed: 03/17/2016
• Issued: 03/27/2018
• Est. Priority Date: 03/17/2016
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Prokhorov, Danil V.
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US15/073,288
• Publication Number:
  US 20170270916A1
• Time in Patent Office: 740 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

The processing of voice inputs includes receiving a voice input from a user. The received voice input can be analyzed to determine whether the voice input includes at least one of human-intended content or machine-intended content. Responsive to determining that the voice input includes human-intended content, a human recipient for the human-intended content can be identified within the voice input, and a message can be sent to the identified human recipient. The message can include the human-intended content in an audio form. Responsive to determining that the voice input includes machine-intended content, a machine recipient for the machine-intended content can be identified within the voice input, and a message including the machine-intended content can be sent to the identified machine recipient to implement the machine-intended content.

Claims

1. A method of processing voice inputs, the method comprising:

receiving a voice input from a user;

analyzing, using a processor, the received voice input for human-intended content and machine-intended content;

when the voice input includes human-intended content;

identifying within the voice input a human recipient for the human-intended content; and

sending a message to the identified human recipient, the message including the human-intended content in an audio form; and

when the voice input includes machine-intended content;

identifying within the voice input a machine recipient for the machine-intended content; and

sending a message including the machine-intended content to the identified machine recipient, whereby the machine-intended content is processed for implementation by the identified machine recipient.

2. The method of claim 1, wherein analyzing the received voice input to determine whether the voice input includes at least one of human-intended content or machine-intended content includes analyzing the received voice input using natural language processing.

3. The method of claim 1, wherein receiving the voice input includes receiving the voice input directly from a human user at voice interface located onboard a vehicle.

4. The method of claim 1, wherein receiving the voice input includes receiving the voice input indirectly from a human user at a remote voice interface.

5. The method of claim 1, further including generating an audio file including the human intended content, and wherein the message includes the audio file.

6. The method of claim 1, wherein the human intended content is not converted to text.

7. The method of claim 1, further including converting the machine intended content into a format that is compatible for processing by the identified machine recipient.

8. A voice input system comprising:

a voice interface configured to receive voice inputs from a human user, the voice interface including one or more microphones; and

one or more processors operatively connected to receive voice inputs from the voice interface, the one or more processors being programmed to initiate executable operations comprising;

analyzing a received voice input for human-intended content and machine-intended content;

when the voice input includes human-intended content;

identifying within the voice input a human recipient for the human-intended content; and

sending a message to the identified human recipient, the message including the human-intended content in an audio form, and

when the voice input includes machine-intended content;

identifying within the voice input a machine recipient for the machine-intended content; and

sending a message including the machine-intended content to the identified machine recipient, whereby the machine-intended content is processed for implementation by the identified machine recipient.

9. The system of claim 8, wherein analyzing the received voice input for human-intended content and machine-intended content includes analyzing the received voice input using natural language processing.

10. The system of claim 8, wherein the voice interface is located onboard a vehicle, and wherein the voice input is received directly from a vehicle occupant at the voice interface.

11. The system of claim 8, wherein the voice interface is located onboard a vehicle, and wherein the voice input is received indirectly from a human user at a remote voice interface communicatively linked to the voice interface.

12. The system of claim 8, further including generating an audio file including the human intended content, and wherein the message includes the audio file.

13. The system of claim 8, wherein the human intended content is not converted to text.

14. The system of claim 8, further including converting the machine intended content into a format that is compatible for processing by the identified machine recipient.

21. The system of claim 8, wherein analyzing the received voice input for human-intended content and machine-intended content is not performed in real-time.

22. The system of claim 8, wherein the machine-intended content includes user payment information.

23. The system of claim 8, wherein the machine-intended content includes user preference data.

24. The system of claim 8, wherein analyzing the received voice input for human-intended content and machine-intended content includes comparing the received voice input to a predefined limited vocabulary.

25. The system of claim 8, wherein the audio form is selected based on preference data associated with the identified human recipient.

15. A vehicle comprising:

a voice interface located onboard the vehicle, the voice interface being configured to receive voice inputs; and

a processor operatively connected to receive voice inputs from the voice interface, the processor being programmed to initiate executable operations comprising;

receiving a voice input from the voice interface;

analyzing, using natural language processing, the received voice input for human-intended content and machine-intended content;

when the voice input includes human-intended content;

identifying within the voice input a human recipient for the human-intended content;

generating an audio file including the human intended content of the voice input; and

sending a message to the identified human recipient, the message including the audio file, wherein the human intended content is not converted to text; and

when the voice input includes machine-intended content;

identifying within the voice input a machine recipient for the machine-intended content;

converting the machine-intended content into a format that is compatible for processing by the identified machine recipient; and

sending a message including the converted machine-intended content to the identified machine recipient, whereby the machine-intended content is processed for implementation by the identified machine recipient.

16. The vehicle of claim 15, wherein the voice interface is configured to receive voice inputs directly from a vehicle occupant at the voice interface.

17. The vehicle of claim 15, wherein the voice interface is configured to receive voice inputs indirectly from a human user at a remote computing device communicatively linked to the voice interface.

18. The vehicle of claim 15, wherein the voice interface includes one or more microphones.

19. A computer program product for processing voice inputs, the computer program product comprising a non-transitory computer readable storage medium having program code embodied therein, the program code executable by a processor to perform a method comprising:

analyzing a received voice input for human-intended content and machine-intended content;

when the voice input includes human-intended content;

identifying within the voice input a human recipient for the human-intended content; and

sending a message to the identified human recipient, the message including the human-intended content in an audio form; and

when the voice input includes machine-intended content;

identifying within the voice input a machine recipient for the machine-intended content; and

sending a message including the machine-intended content to the identified machine recipient, whereby the machine-intended content is processed for implementation by the identified machine recipient.

20. The computer program product of claim 19, wherein analyzing the received voice input for human-intended content and machine-intended content includes analyzing the received voice input using natural language processing.