Systems and methods for off-board voice-automated vehicle navigation

• US 9,026,355 B2
• Filed: 04/15/2014
• Issued: 05/05/2015
• Est. Priority Date: 09/10/2004
• Status: Active Grant

• Current Assignee: Sirius XM Connected Vehicle Services Inc. (Liberty Media Corporation)
• Original Assignee: Sirius XM Connected Vehicle Services Inc. (Liberty Media Corporation)
• Inventors: Schalk, Thomas Barton
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): PIPALA, EDWARD J
• Application Number:
  US14/253,081
• Publication Number:
  US 20140229108A1
• Time in Patent Office: 385 Days
• Field of Search: 701/400, 701/408, 701/409, 701/410, 701/419, 701/420, 701/427, 701/443, 340/988, 340/989, 340/990, 340/993, 340/995.12, 340/995.16, 340/995.24, 340/996
• US Class Current: 701/410
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence

Abstract

A system for providing navigational information to a vehicle driver. An on-board system is disposed on a vehicle and processes and transmits to a data center, via a wireless link, spoken requests from a vehicle driver requesting navigational information. The data center performs automated voice recognition on the received spoken requests to attempt recognition of destination components of the spoken requests, generates a list of possible destination components corresponding to the spoken requests, assigns a confidence score for each of the possible destination components on the list, determines if a possible destination component with a highest confidence score has a confidence score above a selected threshold, and computer-generates a representation of the possible destination components for transmission to the on-board system via the wireless link for confirmation by the vehicle driver if the highest confidence score of every possible destination component is above the selected threshold.

Claims

1. A system for providing navigational information to a vehicle driver, comprising:

an on-board system disposed on a vehicle and processing and transmitting via a wireless link spoken requests from a vehicle driver requesting navigational information to a desired destination; and

a data center processing the spoken requests received via the wireless link, wherein the data center;

performs automated voice recognition processing on the spoken requests to attempt recognition of destination components of the spoken requests;

generates and stores a list of possible destination components corresponding to the spoken requests and confidence scores calculated for each possible destination component;

confirms an accuracy of the possible destination components via fully automated interactive voice exchanges between the vehicle driver and the data center when the confidence scores calculated for all of the possible destination components are above a selected threshold;

determines a destination from confirmed destination components;

generates navigational information to the determined destination; and

transmits the navigational information to the on-board system via the wireless link.

2. The system according to claim 1, wherein the fully automated interactive voice exchanges confirming the accuracy of the possible destination components comprises:

transmitting a computer-generated representation of the possible destination components to the vehicle driver via the wireless link; and

prompting the vehicle driver via the wireless link to confirm the accuracy of the possible destination components.

3. The system according to claim 1, wherein, when the confidence score calculated for at least one possible destination component of the spoken requests is below the selected threshold, the data center:

transmits a stored recording of the at least one below-threshold possible destination component as spoken by the vehicle driver in the spoken requests to the vehicle driver via the wireless link; and

prompts the vehicle driver via the wireless link to aurally confirm the accuracy of the stored recording of the at least one below-threshold possible destination component of the spoken requests.

4. The system according to claim 3, wherein the data center selectively allows intervention of a data center operator upon positive confirmation by the vehicle driver of the accuracy of the stored recording of the at least one below-threshold possible destination component.

5. The system according to claim 4, wherein intervention of a data center operator comprises:

presenting to a data center operator the generated list of possible destination components of the spoken requests and the confidence score calculated for each of the possible destination components;

playing back the positively confirmed stored recording of the spoken requests of the vehicle driver to the data center operator for analysis by the data center operator; and

determining the destination from information received from the data center operator that identifies the at least one below-threshold possible destination component.

6. The system according to claim 1, wherein the destination components include at least one of:

address number;

street name;

city;

state; and

point of interest.

7. The system according to claim 1, wherein the data center generates the navigational information based upon position information received from the on-board system via the wireless link.

8. The system according to claim 1, wherein the selected threshold is zero.

9. The system according to claim 1, wherein the selected threshold is non-zero.

10. The system according to claim 2, wherein the computer-generated representation is a text-to-speech format.

11. A system for providing navigational information to a vehicle driver, comprising:

an on-board system disposed on a vehicle and processing and transmitting via a wireless link spoken requests from a vehicle driver requesting navigational information to a desired destination;

a data center processing the spoken requests received via the wireless link, wherein the data center;

performs automated voice recognition processing on the spoken requests to attempt recognition of destination components of the spoken requests;

generates a list of possible destination components corresponding to the spoken requests;

assigns a confidence score for each of the possible destination components on the list;

determines if a possible destination component with a highest confidence score has a confidence score above a selected threshold; and

computer-generates a representation of the possible destination components for transmission to the on-board system via the wireless link for confirmation by the vehicle driver if the highest confidence score of every possible destination component is above the selected threshold.

12. The system according to claim 11, wherein the data center further:

determines a destination from confirmed destination components;

generates navigational information to the determined destination; and

transmits the navigational information to the on-board system via the wireless link.

13. The system according to claim 11, wherein the data center further:

determines if the highest confidence score of a possible destination component is below the selected threshold; and

plays back a recording in the voice of the vehicle driver of at least the possible destination component with the highest confidence score below the threshold to the vehicle driver via the on-board system for confirmation by the vehicle driver.

14. The system according to claim 13, wherein the data center selectively allows the intervention of a data center operator upon positive confirmation by the vehicle driver of the accuracy of the recording.

15. The system according to claim 14, wherein intervention of a data center operator comprises:

presenting to a data center operator the generated list of possible destination components of the spoken requests and the confidence scores assigned for each of the possible destination components;

playing back the positively confirmed recording of the spoken requests of the vehicle driver to the data center operator for analysis by the data center operator; and

determining the destination from information received from the data center operator that identifies the possible destination component with the highest confidence score below the threshold.

16. The system according to claim 11, wherein the destination components include at least one of:

address number;

street name;

city;

state; and

point of interest.

17. The system according to claim 11, wherein the data center generates the navigational information based upon position information received from the on-board system via the wireless link.

18. The system according to claim 11, wherein the selected threshold is zero.

19. The system according to claim 11, wherein the selected threshold is non-zero.

20. The system according to claim 11, wherein the computer-generated representation is a text-to-speech format.