Voice recognition apparatus, vehicle having the same, and control method of voice recognition apparatus

• US 10,629,210 B2
• Filed: 06/22/2017
• Issued: 04/21/2020
• Est. Priority Date: 01/09/2017
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Motors Corporation (Kia Corp.)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Kim, BiHo
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US15/630,076
• Publication Number:
  US 20180197546A1
• Time in Patent Office: 1,034 Days
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• CPC Class Codes: 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
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/20 Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions

Abstract

A voice recognition apparatus may include a receiver configured to receive a voice command; a provider configured to output a guidance message; and a controller configured to control the provider in response to the voice command, analyze a listening pattern of the guidance message transmitted by the receiver, and adjust an output of the guidance message based on the listening pattern.

Claims

1. A voice recognition apparatus comprising;

a receiver configured to receive a voice command;

a provider configured to output a guidance message; and

a controller configured to control the provider in response to the voice command, analyze a listening pattern of the guidance message transmitted by the receiver, and control an output of the guidance message based on the listening pattern,

wherein the listening pattern includes listening times from when the outputting of the guidance message is started to when the outputting of the guidance message is stopped by a user'"'"'s input, and

wherein the controller compares the listening times with a predetermined time, and determines a short-length guidance message based on a result of comparing the listening times with the predetermined time,

wherein when the listening times are equal to or greater than the redetermined time, the controller is configured to output the determined short-length guidance message shorter than the guidance message in length, and

wherein the controller compares the determined short-length guidance message with the listening times and controls an output seed of the determined short-length guidance message based on a result of comparing the determined short-length guidance message with the listening times.

2. The voice recognition apparatus according to claim 1, wherein

the listening pattern includes an average of the listening times for the guidance message.

3. The voice recognition apparatus according to claim 1, wherein

when the listening pattern is shorter than the predetermined time, the controller is configured to control the provider to output a beep sound without outputting the guidance message.

4. The voice recognition apparatus according to claim 1, wherein

when the controller receives a new voice command from the user while the guidance message is being output, the controller is configured to stop outputting the guidance message.

5. The voice recognition apparatus according to claim 1, further including a voice command database configured to store the listening times, wherein the controller is configured to control the output of the guidance message based on an average of the listening times stored in the voice command database.

6. A vehicle comprising:

a receiver configured to receive a voice command;

an Audio Video Navigation (AVN) terminal configured to output a service including a guidance message; and

a controller configured to control the AVN terminal in response to the voice command, analyze a listening pattern for the guidance message transmitted by the receiver, and control an output of the guidance message based on the listening pattern,

wherein the listening pattern includes listening times from when the outputting of the guidance message is started to when the outputting of the guidance message is stopped by a user'"'"'s input, and

wherein the controller compares listening times with a predetermined time, and determines a short-length guidance message based on a result of comparing the listening times with the predetermined time,

wherein when the listening times are equal to or greater than the predetermined time, the controller is configured to output the determined short-length guidance message shorter than the guidance message in length, and

wherein the controller compares the determined short-length guidance message with the listening times and then controls an output speed of the determined short-length guidance message based on a result of comparing the determined short-length guidance message with the listening times.

7. The vehicle according to claim 6, wherein the listening pattern includes an average of the listening times for the guidance message.

8. The vehicle according to claim 6, wherein, when the listening pattern is shorter than the predetermined time, the controller is configured to output a beep sound without outputting the guidance message.

9. The vehicle according to claim 6, wherein the AVN terminal further includes a display configured to recognize the user'"'"'s touch, and

upon receiving the user'"'"'s touch during the output of the guidance message, the controller is configured to stop outputting the guidance message.

10. The vehicle according to claim 6, further including a voice command database configured to store the listening pattern, wherein the controller is configured to control the output of the guidance message based on an average of the listening times stored in the voice command database.

11. A control method of a voice recognition apparatus, the control method comprising:

receiving at least one of a user'"'"'s input and a voice command;

outputting, by a controller, a guidance message corresponding to the at least one of the user'"'"'s input and the voice command;

analyzing, by the controller, a listening pattern for the guidance message; and

adjusting, by the controller, an output of the guidance message based on the listening pattern,

wherein the listening pattern includes listening times from when the outputting of the guidance message is started to when the outputting of the guidance message is stopped by the user'"'"'s input,

wherein the analyzing includes comparing the listening times with a predetermined time and the adjusting includes determining a short-length guidance message based on a result of comparing the listening times with the predetermined time,

wherein the outputting of the guide message includes determining of the short-length guidance message shorter than the guidance message in length, when the listening times re equal to or greater than the predetermined time, and

wherein the analyzing further includes comparing the determined short-length guidance message with the listening times and the adjusting further includes controlling of output speed of the determined short-length guidance message based on a result of comparing the determined short-length guidance message with the listening times.

12. The method according to claim 11, wherein the outputting includes stopping the output of the guidance message according to the user'"'"'s input after the guidance message is output.

13. The method according to claim 11, wherein the outputting includes stopping the output of the guidance message when the voice command is received while the guidance message is being output.

14. The voice recognition method according to claim 12, wherein the outputting of the guidance message includes continuously outputting the guidance message when an input time of the voice command is shorter than the predetermined time.

15. The voice recognition method according to claim 11, wherein the outputting of the guidance message includes outputting the controlled guidance message, when the at least one of the user'"'"'s input and the voice command is received again.