System and method for providing a natural language voice user interface in an integrated voice navigation services environment

• US 8,719,026 B2
• Filed: 02/04/2013
• Issued: 05/06/2014
• Est. Priority Date: 12/11/2007
• Status: Active Grant

• Current Assignee: Cerence Inc.
• Original Assignee: VoiceBox Technologies Corporation (Microsoft Corporation)
• Inventors: Menaker, Sam, Zimmerman, Bernie, Dichristo, Philippe, Armstrong, Lynn, Guttigoli, Sheetal, Tjalve, Michael, Salomon, Ari, Baldwin, Larry, Cheung, Catherine, Kennewick, Michael R.
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US13/758,170
• Publication Number:
  US 20130211710A1
• Time in Patent Office: 456 Days
• Field of Search: 704 1- 10, 704/251, 704/252, 704/255, 704/257, 704/270, 704/270.1
• US Class Current: 704/257
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G06Q 30/0261 based on user location
• 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 15/08 Speech classification or search
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A conversational, natural language voice user interface may provide an integrated voice navigation services environment. The voice user interface may enable a user to make natural language requests relating to various navigation services, and further, may interact with the user in a cooperative, conversational dialogue to resolve the requests. Through dynamic awareness of context, available sources of information, domain knowledge, user behavior and preferences, and external systems and devices, among other things, the voice user interface may provide an integrated environment in which the user can speak conversationally, using natural language, to issue queries, commands, or other requests relating to the navigation services provided in the environment.

Claims

1. A method for providing a natural language voice user interface, the method being implemented on a computer system including one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising:

receiving, by the one or more physical processors, a natural language utterance from an input device associated with a navigation device, wherein the natural language utterance relates to navigation;

determining, by the one or more physical processors, a current location of the navigation device;

selecting, by the one or more physical processors from among a plurality of sets of location-specific grammar information, a set of location-specific grammar information based on proximity between the current location and a location associated with the set of location-specific grammar information;

determining, by the one or more physical processors, an amount of available resources for processing the natural language utterance;

determining, by the one or more physical processors, a size threshold for a recognition grammar based on the amount of available resources;

generating, by the one or more physical processors, the recognition grammar with the set of location-specific grammar information based on the size threshold such that a size of the recognition grammar does not exceed the size threshold;

determining, by the one or more physical processors, one or more interpretations of the natural language utterance based on the recognition grammar;

determining, by the one or more physical processors based on the one or more interpretations, a destination; and

determining, by the one or more physical processors, a route from the current location to the destination.

2. The method of claim 1, wherein determining the route comprises:

determining at least a portion of the route based on the one or more interpretations of the natural language utterance;

receiving a subsequent natural language utterance relating to the natural language utterance;

determining one or more interpretations of the subsequent natural language utterance based on at least the portion of the route; and

determining a remaining portion of the route based on the one or more interpretations of the subsequent natural language utterance.

3. The method of claim 1, wherein determining the one or more interpretations of the natural language utterance comprises:

recognizing, during a first pass by the one or more physical processors, one or more words in the natural language utterance that define a navigation command; and

recognizing, during a second pass by the one or more physical processors, one or more additional words in the natural language utterance that define the destination.

4. The method of claim 1, further comprising:

dynamically recalculating, by the one or more physical processor, the route in response to one or more subsequent interactions with a user refining the destination.

5. The method of claim 4, wherein dynamically recalculating the route comprises generating directions from the current location to the refined destination.

6. The method of claim 1, wherein generating the recognition grammar comprises loading at least a portion of the set of location-specific grammar information.

7. The method of claim 1, wherein the destination is associated with a full or partial address, and wherein determining the route comprises:

identifying multiple destinations associated with addresses that correspond to the full or partial address;

ranking the multiple identified destinations according to proximities to the current location or the full or partial address; and

selecting one of the multiple identified destinations having a highest ranking.

8. The method of claim 1, wherein each of the plurality of sets of location-specific grammar information corresponds to a different subdivision, neighborhood, city, or county, and wherein the selected set of location-specific grammar information corresponds to a subdivision, neighborhood, city, or county that is most proximal, among the plurality of sets, to the current location.

9. The method of claim 1, further comprising:

generating, by the one or more physical processors, dynamic directions to provide a guide on the route from the current location to the destination using a navigation-specific information source.

10. The method of claim 1, further comprising:

dynamically recalculating, by the one or more physical processors, the route in response to a managed dialogue resolving the destination, wherein dynamically recalculating the route includes generating directions from the current location to the resolved destination.

11. A system for providing a natural language voice user interface, comprising:

one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to;

receive a natural language utterance from an input device associated with a navigation device, wherein the natural language utterance relates to navigation;

determine a current location of the navigation device;

select, from among a plurality of sets of location-specific grammar information, a set of location-specific grammar information based on proximity between the current location and a location associated with the set of location-specific grammar information;

determine an amount of available resources for processing the natural language utterance;

determine a size threshold for a recognition grammar based on the amount of available resources;

generate the recognition grammar with the set of location-specific grammar information based on the size threshold such that a size of the recognition grammar does not exceed the size threshold;

determine one or more interpretations of the natural language utterance based on the recognition grammar;

determine, based on the one or more interpretations, a destination; and

determine a route from the current location to the destination.

12. The system of claim 11, wherein determining the route comprises:

determining at least a portion of the route based on the one or more interpretations of the natural language utterance;

receiving a subsequent natural language utterance relating to the natural language utterance;

determining one or more interpretations of the subsequent natural language utterance based on at least the portion of the route; and

determining a remaining portion of the route based on the one or more interpretations of the subsequent natural language utterance.

14. The system of claim 11, wherein the one or more physical processors are further caused to:

dynamically recalculate the route in response to one or more subsequent interactions with a user refining the destination.

15. The system of claim 14, wherein dynamically recalculating the route comprises generating directions from the current location to the refined destination.

16. The system of claim 11, wherein generating the recognition grammar comprises loading at least a portion of the set of location-specific grammar information.

17. The system of claim 11, wherein the destination is associated with a full or partial address, and wherein determining the route comprises:

identifying multiple destinations associated with addresses that correspond to the full or partial address;

ranking the multiple identified destinations according to proximities to the current location or the full or partial address; and

selecting select one of the multiple identified destinations having a highest ranking.

18. The system of claim 11, wherein each of the plurality of sets of location-specific grammar information corresponds to a different subdivision, neighborhood, city, or county, and wherein the selected set of location-specific grammar information corresponds to a subdivision, neighborhood, city, or county that is most proximal, among the plurality of sets, to the current location.

19. The system of claim 11, wherein the one or more physical processors are further caused to:

generate, based on a navigation-specific information source, dynamic directions to provide a guide on the route from the current location to the destination.

20. The system of claim 11, wherein the one or more physical processors are further caused to:

dynamically recalculate the route in response to a managed dialogue resolving the destination; and

generate directions from the current location to the resolved destination to dynamically recalculate the route.

13. The system of 11, wherein determining the one or more interpretations of the natural language utterance comprises:

recognize, during a first pass, one or more words in the natural language utterance that define a navigation command;

recognize, during a second pass, one or more additional words in the natural language utterance that define the destination.