Voice user interface authoring tool

• US 8,315,874 B2
• Filed: 04/11/2006
• Issued: 11/20/2012
• Est. Priority Date: 12/30/2005
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Barton, William F., Spina, Michelle S., Ollason, David G., Odell, Julian J.
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): ROBERTS, SHAUN A
• Application Number:
  US11/401,823
• Publication Number:
  US 20070156406A1
• Time in Patent Office: 2,415 Days
• Field of Search: 704/277, 704/257, 704/251, 704/270, 704/270.1, 704/275
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• 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 voice user interface authoring tool is configured to use categorized example caller responses, from which callflow paths, automatic speech recognition, and natural language processing control files can be generated automatically within a single, integrated authoring user interface. A voice user interface (VUI) design component allows an author to create an application incorporating various types of action nodes, including Prompt/Response Processing (PRP) nodes. At runtime, the system uses the information from each PRP node to prompt a user to say something, and to process the user'"'"'s response in order to extract its meaning. An Automatic Speech Recognition/Natural Language Processing (ASR/NLP) Control Design component allows the author to associate sample inputs with each possible meaning, and automatically generates the necessary ASR and NLP runtime control files. The VUI design component allows the author to associate the appropriate ASR and NLP control files with each PRP node, and to associate an action node with each possible meaning, as indicated by the NLP control file.

Claims

1. A method of generating a voice user interface implemented by a computing device, the method comprising:

providing a response container for governing voice response processing for the voice user interface;

providing a plurality of nodes associated with the response container and defining acts to be performed;

providing a plurality of response classes defining types of voice input responses related to the plurality of nodes associated with the response container;

automatically generating a flow path for each of the plurality of response classes in the response container, each flow path spanning from a first node defining a first act to be performed to a second node defining a second act to be performed, wherein the generating the flow path for each of the plurality of response classes determines a callflow sequence of execution of acts of the plurality of nodes according to a response class associated with a voice input response;

receiving meanings of different possible answers expected in response to the plurality of nodes;

receiving sample inputs associated with each of the received meanings;

automatically generating control files to extract a meaning and to determine a response class associated with a received voice response based on the received meanings of different possible answers and the received sample inputs; and

automatically assigning a flow path to the received voice response based on an extracted meaning and a determined response class for establishing a callflow sequence in response to the received voice response.

2. The method of claim 1, further comprising enabling an author to configure one or more additional response containers and to assign one or more of the response classes to the response containers.

3. The method of claim 2, further comprising enabling an author to associate one or more of the additional response containers with a corresponding prompt node.

4. The method of claim 1, wherein a response class includes a keyword container comprising one or more keyword values, wherein a processor automatically generates a flow path for each of the keywords associated with the response class.

5. The method of claim 1, wherein the automatically generating control files further comprises assigning automatic speech recognition and natural language processing control files to the response containers.

6. The method of claim 1, wherein the providing a plurality of nodes comprises providing at least one prompt node prompting a spoken response to be provided.

7. The method of claim 1, wherein the providing a plurality of nodes comprises providing at least one action node defining an action to be performed.

8. The method of claim 7, wherein the action node comprises a node associated with an announcement action.

9. The method of claim 7, wherein the action node comprises a node associated with a transaction.

10. The method of claim 1, further comprising using learned sample inputs to generate revised automatic speech recognition component control files.

11. The method of claim 1, further comprising using format rules to generate one or more natural language processing control files.

12. The method of claim 1, further comprising:

measuring characteristics of the received sample inputs; and

using the characteristics to create a classifier configured for providing an indication of which of the response classes corresponds to subsequent speech inputs.

13. The method of claim 12, further comprising evaluating a level of confidence for the indication of which of the response classes corresponds to subsequent speech inputs.

14. The method of claim 13, further comprising providing one or more options for corrective action if the level of confidence for the indication of which of the response classes corresponds to a subsequent speech input is below a selected threshold.

15. A computer readable storage medium comprising instructions readable by a computing device, the instructions enabling the computing device to execute a voice user interface authoring tool, the instructions comprising:

an automatic speech recognition component; and

a voice user interface design component implemented on a processor of the computing device to provide a response container for governing voice response processing for a voice user interface, to provide a plurality of nodes associated with the response container and defining acts to be performed, to provide a plurality of response classes defining types of voice input responses related to the plurality of nodes associated with the response container, to automatically generate a flow path for each of the plurality of response classes in the response container, each flow path spanning from a first node defining a first act to be performed to a second node defining a second act to be performed, wherein the generating the flow path for each of the plurality of response classes determines a callflow sequence of execution of acts of the plurality of nodes according to a response class associated with a voice input response, to receive meanings of different possible answers expected in response to the plurality of nodes, to receive sample inputs associated with each of the received meanings, to automatically generate control files to extract a meaning and to determine a response class associated with a received voice response based on the received meanings of different possible answers and the received sample inputs and to automatically assign a flow path to the received voice response based on an extracted meaning and a determined response class for establishing a callflow sequence in response to the received voice response.