Enabling legacy interactive voice response units to accept multiple forms of input

• US 7,054,421 B2
• Filed: 05/31/2002
• Issued: 05/30/2006
• Est. Priority Date: 05/31/2002
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Mandalia, Baiju D., Kandlur, Dilip D., Lindquist, Dave B.
• Primary Examiner(s): WOO, STELLA L
• Application Number:
  US10/160,517
• Publication Number:
  US 20030223555A1
• Time in Patent Office: 1,460 Days
• Field of Search: 379/93.15, 379/93.25, 379/93.26, 379/88.01, 379/88.04, 379/88.05, 379/88.13, 379/88.14, 379/88.18, 704/270, 704/275, 704/277
• US Class Current: 379/93.15
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A method of enabling a legacy interactive voice response unit to accept multiple forms of user input can include associating dual tone multi-frequency selectable options of the legacy interactive voice response unit with non-dual tone multi-frequency user inputs. A non-dual tone multi-frequency user input can be received and processed to determine at least one dual tone multi-frequency selectable option that is associated with the received user input. Dual tone multi-frequency signals can be generated for selecting the at least one dual-tone multi-frequency selectable option associated with the user input. The dual tone multi-frequency signals can be provided to the legacy interactive voice response unit.

Claims

1. A method of enabling a legacy interactive voice response unit to accept multiple forms of user input, said method comprising:

associating dual tone multi-frequency selectable options specific to said legacy interactive voice response unit communicatively linked to a telephone network with non-dual tone multi-frequency user inputs, said associating step utilizing code contained within an edge server that is communicatively linked to the telephone network;

receiving a non-dual tone multi-frequency user input;

processing said received user input utilizing the code to determine at least one dual tone multi-frequency selectable option associated with said received user input;

generating dual tone multi-frequency signals for selecting said at least one dual tone multi-frequency selectable option associated with said user input; and

providing said dual tone multi-frequency signals to said legacy interactive voice response unit via the telephone network in a user transparent fashion.

2. The method of claim 1, wherein said legacy interactive voice response unit is incapable of independently performing speech recognition, and wherein said received non-dual tone multi-frequency user input comprises a user spoken utterance, wherein said processing step further comprises speech recognizing said user spoken utterance to determine a textual representation of said user spoken utterance prior to determining said at least one dual tone multi-frequency selectable option.

3. The method of claim 1, wherein said non-dual tone multi-frequency user input is received by said edge server across a computer communications network, wherein said non-dual tone multi-frequency input is selected from the group consisting of keystroke input, pointer input, and user input generated from a visual browser.

4. The method of claim 1, further comprising:

identifying a markup language associated with said non-dual tone multi-frequency user input, said code of said processing step being written in a different markup language; and

transcoding said markup language associated with said non-dual tone multi-frequency user input to said different markup language during said processing step.

5. The method of claim 4, wherein the code of said processing step is when in an eXtensible Markup Language(XML).

6. The method of claim 4, wherein the non-dual tone multi-frequency user input comprises a user spoken utterance, and wherein the markup language associated with said non-dual tone multi-frequency user input is a markup language designed for voice based interaction.

7. The method of claim 4, wherein the non-dual tone multi-frequency user input comprises user input generated from a visual browser, and wherein the markup language associated with said non-dual tone multi-frequency user input is a HyperText Markup Language(HTML).

8. The method of claim 1, further comprising:

receiving a response from said interactive voice response unit;

interpreting said response utilizing code of the edge server written in a markup language;

identifying a markup language associated with presenting the response to a response recipient;

transcoding said interpreted response from the markup language of the edge server to the markup language associated with presenting the response to the response recipient.

9. The method of claim 1, further comprising:

receiving a call processing instruction from said legacy interactive voice response unit; and

routing said call processing instruction to a node in the telecommunications network.

10. A system for enabling a legacy voice response unit which is incapable of independently performing speech recognition to accept multiple forms of user input, said system comprising:

at least one interface configured to receive user input directed to said legacy interactive voice response unit;

a data store comprising a plurality of possible non-dual tone multi-frequency user inputs and associated dual tone multi-frequency selectable options specific to said legacy interactive voice response unit; and

a dual tone multi-frequency processor configured to determine dual tone multi-frequency selectable options from received user inputs according to said data store and to generate dual tone multi-frequency signals in a user transparent fashion, wherein said dual tone multi-frequency signals are understandable by said legacy voice response unit for selecting said dual tone multi-frequency selectable options, and wherein said data store and said dual tone multi-frequency processor are disposed within an edge server of a telephony network.

11. The system of claim 10, further comprising:

a legacy voice response unit which is incapable of independently performing speech recognition, wherein said at least one interface is configured to receive user spoken utterances, wherein selected ones of the dual tone multi-frequency user inputs comprise speech-to-text conversions of said user spoken utterances.

12. The system of claim 10, wherein said legacy voice response unit is capable of accepting only dual tone multi-frequency input, wherein user-input for which said at least one interface is configured comprise input other than dual tone multi-frequency input.

13. The system of claim 12, further comprising:

a transcoder configured to convert content between one modality associated with said legacy voice response unit to at least a second and different modality associated with the at least one interface.

14. The system of claim 13, wherein one interface of the at least one interface includes a Web browser, and wherein the markup language associated with one interface is a Web based markup language.

15. The system of claim 10, wherein said transcoder is configured to transcode content from at least one markup language associated with one of the at least one interface to another markup language used by the dual tone multi-frequency processor.

16. The system of claim 15, wherein said interface is configured to receive speech input, said system further comprising:

a speech processing system configured to utilize code written in a markup, language designed for voice based interaction to convert received speech to text and to convert text to an audio stream, wherein the markup language of the code is the same as the at least one markup language associated with the at least one interface.

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

associating dual tone multi-frequency selectable options specific to said legacy interactive voice response unit communicatively linked to a telephone network with non-dual tone multi-frequency user inputs, said associating step utilizing code contained within an edge server that is communicatively linked to the telephone network;

receiving a non-dual tone multi-frequency user input;

processing said received user input utilizing the code to determine at least one dual tone multi-frequency selectable option associated with said received user input;

generating dual tone multi-frequency signals for selecting said at least one dual tone multi-frequency selectable option associated with said user input; and

providing said dual tone multi-frequency signals to said legacy interactive voice response unit via the telephone network in a user transparent fashion.

18. The machine-readable storage of claim 17, wherein said legacy interactive voice response unit is incapable of independently performing speech recognition, and wherein said received non-dual tone multi-frequency user input comprises a user spoken utterance, wherein said processing step further comprises speech recognizing said user spoken utterance to determine textual representation of said user spoken utterance prior to determining said at least one dual tone multi-frequency selectable option.

19. The machine-readable storage of claim 17, wherein said non-dual tone multi-frequency user input is received by said edge server across a computer communications network, wherein said non-dual tone multi-frequency input is selected from the group consisting of keystroke input, pointer input, and user input generated from a visual browser.

20. The machine-readable storage of claim 17, said identifying step further comprising:

identifying a markup language associated with said non-dual tone multi-frequency user input, said code of said processing step being written in a different markup language; and

transcoding said markup language associated with said non-dual tone multi-frequency user input to said different markup language during said processing step.

21. The machine-readable storage of claim 17, farther comprising:

receiving a response from said interactive voice response unit;

interpreting said response utilizing code of the edge server written in a markup language;

identifying a markup language associated with presenting the response to a response recipient;

transcoding said interpreted response from the markup language of the edge server to the markup language associated with presenting the response to the response recipient.

22. The machine-readable storage of claim 17, further comprising:

receiving a call processing instruction from said legacy interactive voice response unit; and

routing said call processing instruction to a node in the telecommunications network.