SYSTEM AND METHOD OF USING MODULAR SPOKEN-DIALOG COMPONENTS

• US 20080306743A1
• Filed: 08/19/2008
• Published: 12/11/2008
• Est. Priority Date: 03/01/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Di Fabbrizio, Giuseppe, Lewis, Charles Alfred
• Granted Patent: US 7,778,836 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A system and method are disclosed for switching contexts within a spoken dialog between a user and a spoken dialog system. The spoken dialog system utilizes modular subdialogs that are invoked by at least one flow controller that is a finite state model and that associated with a dialog manager. The spoken dialog system includes a dialog manager with a flow controller and a reusable subdialog module. The method includes, while the spoken dialog is being controlled by the subdialog module that was invoked by the flow controller, receiving context-changing input associated with speech from a user that changes a dialog context and comparing the context-changing input to at least one context shift. And, if any of the context shifts are activated by the comparing step, then passing control of the spoken dialog to the flow controller with context shift message and destination state.

Claims

1. A spoken dialog system that switches contexts within a spoken dialog between a user, the spoken dialog system comprising:

a dialog manager with a first-flow controller and a second-flow controller, each of the first-flow controller and the second-flow controller being a finite state model;

a module configured, while the spoken dialog is being controlled by the first-flow controller, to receive context-changing input associated with speech from a user that changes the dialog context;

a module configured to compare the context-changing input to a table of context shifts;

a module configured, if any of the context shifts are activated by the comparison, to pass control to an invoked second flow controller indicated by the context shift;

a module configured, if no context shift is activated by the comparison, to maintain control of the spoken dialog with the first controller; and

a module configured to store a local context associated with each of the first and second-flow controllers, the local context maintaining a state of the flow controller that is independent of the implemented dialogs, wherein the second-flow controller receives data values stored in the local context of the first-flow controller.

2. The spoken dialog system of claim 1, further comprising a module configured to maintain a stack of flow controllers wherein each flow controller is added to the stack of flow controllers.

3. The spoken dialog system of claim 2, wherein each invoked flow controller inherits a context shift and becomes the recipient of all user input as part of the spoken dialog interaction until the invoked flow controller relinquishes control of the spoken dialog.

4. A method of switching contexts within a spoken dialog between a user and a spoken dialog system, the spoken dialog system having a dialog manager with a first flow controller and a second flow controller, each of the first flow controller and second flow controller being a finite state model, the method comprising:

receiving user input that causes a change in control from the first flow controller to the second flow controller; and

storing a local context associated with each of the first and second flow controllers, the local context maintaining a state of the flow controller that is independent of implemented subdialogs, wherein the second flow controller receives data values stored in the local context of the first flow controller.

5. The method of claim 4, further comprising:

while the spoken dialog is being controlled by the first flow controller, receiving context-changing input associated with speech from a user that changes a dialog context;

comparing the context-changing input to a table of context shifts;

if any of the context shifts are activated by the comparing step, then passing control to an invoked second flow controller indicated by the context shift; and

if no context shift is activated by the comparing step, then maintaining control of the spoken dialog with the first flow controller.

6. The method of claim 5, further comprising maintaining a stack of flow controllers, wherein each invoked flow controller is added to the stack of flow controllers.

7. The method of claim 6, wherein each invoked flow controller inherits a context shift and becomes the recipient of all user input as part of the spoken dialog interaction until the invoked flow controller relinquishes control of the spoken dialog.

8. A computer-readable medium for storing computer instructions for controlling a computing device to switch contexts within a spoken dialog between a user and a spoken dialog system, the spoken dialog system having a dialog manager with a first flow controller and a second flow controller, each of the first flow controller and second flow controller being a finite state model, the method comprising:

receiving user input that causes a change in control from the first flow controller to the second flow controller; and

storing a local context associated with each of the first and second flow controllers, the local context maintaining a state of the flow controller that is independent of implemented subdialogs, wherein the second flow controller receives data values stored in the local context of the first flow controller.

9. The computer-readable medium of claim 8, further comprising:

while the spoken dialog is being controlled by the first flow controller, receiving context-changing input associated with speech from a user that changes a dialog context;

comparing the context-changing input to a table of context shifts;

if any of the context shifts are activated by the comparing step, then passing control to an invoked second flow controller indicated by the context shift; and

if no context shift is activated by the comparing step, then maintaining control of the spoken dialog with the first flow controller.

10. The computer-readable medium of claim 9, further comprising maintaining a stack of flow controllers, wherein each invoked flow controller is added to the stack of flow controllers.

11. The method of claim 10, wherein each invoked flow controller inherits a context shift and becomes the recipient of all user input as part of the spoken dialog interaction until the invoked flow controller relinquishes control of the spoken dialog.