Open Architecture For A Voice User Interface

• US 20090216540A1
• Filed: 02/20/2009
• Published: 08/27/2009
• Est. Priority Date: 12/08/2000
• Status: Active Grant

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Ben Franklin Patent Holding LLC (Intellectual Ventures LLC)
• Inventors: TESSEL, Marianna, Lange, Danny, Ponomarenko, Eugene, Burkes, Daniel, Oshima, Mitsuru, Tjong, Tjoen Min
• Granted Patent: US 8,005,683 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 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A system and method for processing voice requests from a user for accessing information on a computerized network and delivering information from a script server and an audio server in the network in audio format. A voice user interface subsystem includes: a dialog engine that is operable to interpret requests from users from the user input, communicate the requests to the script server and the audio server, and receive information from the script server and the audio server; a media telephony services (MTS) server, wherein the MTS server is operable to receive user input via a telephony system, and to transfer the user input to the dialog engine; and a broker coupled between the dialog engine and the MTS server. The broker establishes a session between the MTS server and the dialog engine and controls telephony functions with the telephony system.

Claims

1-35. -35. (canceled)

36. A method comprising:

receiving an input from a media communications server via a session established by a broker based on a distribution of processing load;

interpreting a request for information in the input;

communicating the request for information to a network; and

receiving information from the network responsive to the request for information.

37. The method of claim 36, wherein the information comprises a script.

38. The method of claim 37, wherein the script comprises a markup language document.

39. The method of claim 37, further comprising:

interpreting the script to produce one or more prompts; and

sending the one or more prompts to the media communications server.

40. The method of claim 39, wherein the one or more prompts comprise a dynamic audio prompt, the method further comprising:

retrieving an audio file corresponding to the dynamic audio prompt from the network; and

sharing the audio file with the media communications server.

41. The method of claim 39, wherein the one or more prompts comprise an instruction to the media communications server to access an audio file from a shared data area.

42. The method of claim 39, wherein the one or more prompts comprise a text-to-speech request.

43. The method of claim 39, further comprising:

sending an additional one or more prompts to the media communications server in an append instruction.

44. The method of claim 39, further comprising:

instructing the media communications server to play the one or more prompts.

45. The method of claim 39, wherein the one or more prompts comprise a voice recognition instruction, the method comprising:

instructing the media communications server to play the voice recognition instruction; and

receiving a voice recognition result.

46. The method of claim 45, further comprising:

sending a grammar list to the media communications server.

47. A system comprising:

a first communications channel;

a second communications channel; and

one or more processors to;

receive an input from a media communications server via a session established by a broker based on a distribution of processing load, over the first communications channel;

interpret a request for information in the input;

communicate the request for information to a network over the second communications channel; and

receive information from the network responsive to the request for information over the second communications channel.

48. A tangible computer-readable medium having stored thereon computer-executable instructions that, if executed by a computing device, cause the computing device to perform a method comprising:

receiving an input from a media communications server via a session established by a broker based on a distribution of processing load;

interpreting a request for information in the input;

communicating the request for information to a network; and

receiving information from the network responsive to the request for information.

49. A method comprising:

receiving an input from a communications subsystem;

requesting a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;

sending a request for information corresponding to the input to the dialog engine; and

receiving information from the dialog engine corresponding to the request for information.

50. The method of claim 49, further comprising:

performing speech recognition on the received input to generate a speech recognition result, wherein the request for information comprises the speech recognition result.

51. A system comprising:

a first communications channel;

a second communications channel; and

one or more processors to;

receive an input from a communications subsystem over the first communications channel;

request a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;

send a request for information corresponding to the input to the dialog engine over the second communications channel; and

receive information from the dialog engine corresponding to the request for information over the second communications channel.

52. A tangible computer-readable medium having stored thereon computer-executable instructions that, if executed by a computing device, cause the computing device to perform a method comprising:

receiving an input from a communications subsystem;

requesting a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;

sending a request for information corresponding to the input to the dialog engine; and

receiving information from the dialog engine corresponding to the request for information.