Conversation management in speech recognition interfaces

• US 6,199,043 B1
• Filed: 06/24/1997
• Issued: 03/06/2001
• Est. Priority Date: 06/24/1997
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Happ, Alan J.
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/880,819
• Time in Patent Office: 1,351 Days
• Field of Search: 704/275, 704/231, 704/270, 704/251, 704/276, 704/272, 704/260
• US Class Current: 704/272
• 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 first graphical user interface for a video environment display is generated. A second graphical user interface for a synthesized environment display is generated. An audio output interface for audibly transmitting audio information associated with the first and second graphical user interfaces is generated. An audio input interface for receiving audible information as an input for the speech recognition interface is generated. The context is separated from the content by providing video and synthesized environments having different but complementary functions.

Claims

1. A method for managing conversation in a speech recognition interface, comprising the steps of:

capturing video of a non-synthesized human video actor;

concurrently generating a first graphical user interface for displaying said captured video in a video environment display and a second graphical user interface for displaying a computer-synthesized actor in a synthesized environment display;

generating an audio output interface for audibly transmitting audio information associated with said first and second graphical user interfaces; and

,

generating an audio input interface for receiving audible information as an input for said speech recognition interface.

2. The method of claim 1, comprising the step of arranging said video and synthesized environment displays for substantially non overlapping presentation.

3. The method of claim 1, comprising the step of arranging said video and synthesized environment displays for at least partly overlapping presentation.

4. The method of claim 1, comprising the steps of:

originating an information content in at least one of captured video and live video transfer; and

,

originating an information content for said synthesized environment in an acted performance and text-to-speech conversion of speech from said performance.

5. The method of claim 1, comprising the steps of:

establishing a context for said speech recognition interface with said video environment; and

,

providing examples of how to speak and examples of a proper vocabulary with said synthesized environment.

6. The method of claim 1, comprising the steps of:

providing predetermined instructions for using said speech recognition interface with said video environment; and

,

answering questions and supplying information in response to said received audible information with said synthesized environment.

7. The method of claim 1, comprising the steps of:

providing audible information from said video environment in accordance with rules of human-to-human conversation in a lecture format; and

,

providing audible information from said synthesized environment in accordance with rules of human-to-computer conversation.

8. The method of claim 1, comprising the steps of:

initiating new topics, taking turns from said synthesized acting performance and giving turns to said synthesized acting performance with said video environment; and

,

taking turns from said video display, taking turns from said audio input interface, giving turns to said video display and giving turns to said audio input interface with said synthesized environment.

9. The method of claim 1, comprising the step of administering an interview with said speech recognition interface.

10. The method of claim 9, comprising the step managing navigation through said interview with said synthesized environment.

11. The method according to claim 1, wherein said captured video is one of recorded video of a non-synthesized human video actor and live transfer video of a non-synthesized human video actor.