SYSTEM AND METHODS FOR PROMPTING USER SPEECH IN MULTIMODAL DEVICES

• US 20080162143A1
• Filed: 12/27/2006
• Published: 07/03/2008
• Est. Priority Date: 12/27/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Ativanichayaphong, Soonthorn, Agapi, Ciprian, Wilson, Leslie R.
• Granted Patent: US 8,417,529 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• 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 method for prompting user input for a multimodal interface including the steps of providing a multimodal interface to a user, where the interface includes a visual interface having a plurality of input regions, each having at least one input field; selecting an input region and processing a multi-token speech input provided by the user, where the processed speech input includes at least one value for at least one input field of the selected input region; and storing at least one value in at least one input field.

Claims

1. A method for prompting user input for a multimodal interface, the method comprising the steps of:

providing said multimodal interface to a user, said interface comprising a visual interface having a plurality of input regions, wherein each one of said plurality of input regions comprises at least one input field;

selecting one of said plurality of input regions;

processing a multi-token speech input provided by said user;

determining whether said processed speech input includes at least one value for said at least one input field of said selected input region; and

if at least one value for said at least one input field is included in said processed speech input, storing said included at least one value in said at least one input field.

2. The method of claim 1, further comprising the step of:

after said selecting step, generating a prompt for said user to provide said multi-token speech input.

3. The method of claim 2, said prompt comprising visually indicating within said multimodal interface said selected input region.

4. The method of claim 2, said prompt comprising visually indicating within said multimodal interface at least one incomplete input field of said selected input region.

5. The method of claim 2, said prompt comprising audibly indicating said selected input region.

6. The method of claim 1, wherein the selected input region is determined by processing a selection speech input from said user.

7. The method of claim 1, wherein the selected input region is chosen from among one or more of said plurality of input regions having at least one incomplete input field.

8. A system for prompting voice interactions for a multimodal interface comprising a controller element that:

generates said multimodal interface, said interface comprising a visual interface having a plurality of input regions, wherein each one of said plurality of input regions comprises at least one input field;

selects one of said plurality of input regions;

processes a multi-token speech input received by said controller;

determines whether said processed speech input includes at least one value for said at least one input field of said selected input region; and

if at least one value for said at least one input field is included in said processed speech input, stores said at least one value in said at least one input field.

9. The system of claim 8, wherein the controller element that:

after selection of one of said plurality of input regions, generates a prompt requesting said multi-token speech input.

10. The method of claim 9, said prompt comprising visually indicating within said multimodal interface said selected input region.

11. The method of claim 9, said prompt comprising visually indicating within said multimodal interface at least one incomplete input field of said selected input region.

12. The method of claim 9, said prompt comprising audibly indicating said selected input region.

13. The method of claim 8, wherein the controller element selects said selected input region based on a selection speech input received by said controller.

14. The method of claim 8, wherein the controller element selects said selected input region from among one or more of said plurality of input regions having at least one incomplete input field.

15. A machine-readable storage having stored thereon, a computer program having a plurality of code sections, said code sections executable by a machine causing the machine to perform the steps of:

providing a multimodal interface to a user, said interface comprising a visual interface having a plurality of input regions, wherein each one of said plurality of input regions comprises at least one input field;

selecting one of said plurality of input regions;

processing a multi-token speech input provided by said user;

determining whether said processed speech input includes at least one value for said at least one input field of said selected input region; and

if at least one value for said at least one input field is included in said processed speech input, storing said found at least one value in said at least one input field.

16. The method of claim 15, further comprising the step of:

after said selecting step, generating a prompt for said user to provide said multi-token speech input.

17. The method of claim 16, said prompt comprising visually indicating within said multimodal interface said selected input region.

18. The method of claim 16, said prompt comprising visually indicating within said multimodal interface at least one incomplete input field of said selected input region.

19. The method of claim 16, said prompt comprising audibly indicating said selected input region.

20. The method of claim 15, wherein the selected input region is determined by using a selection speech input from said user.