Motor vehicle operating device with a correction strategy for voice recognition

• US 10,176,806 B2
• Filed: 10/22/2015
• Issued: 01/08/2019
• Est. Priority Date: 11/24/2014
• Status: Active Grant

• Current Assignee: Audi AG (Volkswagen AG)
• Original Assignee: Audi AG (Volkswagen AG)
• Inventors: Engelhardt, Doreen
• Primary Examiner(s): Leland, III, Edwin S
• Application Number:
  US15/503,053
• Publication Number:
  US 20170229120A1
• Time in Patent Office: 1,174 Days
• Field of Search: 704257
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/0485 Scrolling or panning
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

The invention relates to a method for operating a motor vehicle, wherein a first speech input of a user is received, at least one recognition result (A-D) is determined by means of a speech recognition system, at least one recognition result (A-D) is output to an output device of the motor vehicle as a result list and a second speech output of the user is received. The objective of the invention is to avoid a double input of false recognition results. In the second speech input, first, a content input repetition of the first speech input is recognized, which points to a correction request of the user. As a result, an excludable portion of the result list is determined and with the determination of a recognition result (C-E) for the second speech input, the excludable portion is excluded as a possible recognition result.

Claims

1. A method for operating a motor vehicle operating device, comprising:

receiving, by a speech detection device, a first speech input of a user,

determining, by a speech recognition device, at least one recognition result for the first speech input, so that at least one recognition result is output at an output device of the motor vehicle as result list, and

receiving, by the speech detection device, a second speech input of the user, wherein a content input repetition of the first speech input is recognized, by a repetition detection device, in the second speech input,

determining, by a control device, an excludable portion of the result list; and

with the determination of the recognition result for the second speech input, the excludable portion is excluded as possible recognition result,

generating, by a signal generating device, a control signal using the recognition result, and

transmitting, by the signal generating device, the control signal to at least one device of the motor vehicle to control the at least one device of the motor vehicle,

wherein at least one of the speech recognition device, the repetition detection device and the output device communicate with the control device so that the control device determines the excludable portion.

2. The method according to claim 1, wherein repetition of the input content is recognized on the basis of at least one of the following criteria:

the user performs a predetermined operation provided for an input correction;

a predetermined correction keyword is recognized in the second speech input;

a predetermined prosodic difference is displayed between the first speech input and the second speech input;

the first speech input and the second speech input agree with each other to a predetermined minimum extent.

3. The method according to claim 1, wherein in order to exclude the excludable portion, the grammar of the speech recognition system is changed.

4. The method according to claim 1, wherein in order to exclude the excludable portion by means of the speech recognition system, at least one standard recognition result is determined for the second speech input and the excludable portion is filtered out from the standard recognition result.

5. The method according to claim 1, wherein as the excludable portion is selected the portion of the result list that was successfully output by the output device to the user is determined.

6. The method according to claim 5, wherein in order to determine the portion that was successfully output, a scrolling operation of the output device is evaluated.

7. The method according to claim 5, wherein an eye movement of the user is detected by means of an eye tracker and to determine the successfully output portion from the result list, and only the successfully output portion is selected from that viewed by the user according to the detected eye movement.

8. The method according to claim 7, wherein the successfully output portion is determined from the result list if the user has viewed this portion for a predetermined minimum period of time.