Methods and apparatus for conversational name dialing systems

• US 6,925,154 B2
• Filed: 05/03/2002
• Issued: 08/02/2005
• Est. Priority Date: 05/04/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Chen, Chengjun Julian, Erdogan, Hakan, Gao, Yuqing, Ramabhadran, Bhuvana, Picheny, Michael A.
• Primary Examiner(s): Foster, Roland G.
• Application Number:
  US10/139,255
• Publication Number:
  US 20020196911A1
• Time in Patent Office: 1,187 Days
• Field of Search: 379 8801- 8804, 37935501-35504, 704/246, 704/247, 704/250, 704/270, 704/276, 704/278, 704/270.1, 455/79, 455/563, 455/564
• US Class Current: 379/88.03
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

Techniques for providing an automated conversational name dialing system for placing a call in response to an input by a user. One technique begins with the step of analyzing an input from a user, wherein the input includes information directed to identifying an intended recipient of a telephone call from the user. At least one candidate for the intended recipient is identified in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary. A confidence measure indicative of a likelihood that the at least one candidate is the intended recipient is determined, and additional information is obtained from the user to increase the likelihood that the at least one candidate is the intended recipient, based on the determined confidence measure.

Claims

1. An automated method of conversational name dialing, the method comprising the steps of:

analyzing an input from a user, wherein the input comprises information directed to identifying an intended recipient of a telephone call from the user;

identifying at least one candidate for the intended recipient, in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary;

determining a confidence measure indicative of a likelihood that the at least one candidate is the intended recipient; and

prompting the user for additional information to increase the likelihood that the at least one candidate is the intended recipient, wherein a prompt type is selectable from a group comprising two or more prompt types, each prompt type obtaining a specified type of additional information from the user, and selected in accordance with the determined confidence measure.

2. The method as recited in claim 1 further comprising the step of confirming the identification of the at least one candidate as the intended recipient.

3. The method as recited in claim 2 further comprising the step of dialing the intended recipient when the identification of the at least one candidate as the intended recipient is confirmed.

4. The method as recited in claim 2 wherein the confirming step includes the step of asking the user a yes or no question.

5. The method as recited in claim 1 further comprising the step of providing feedback to the user to increase the likelihood that the at least one candidate is the intended recipient.

6. The method as recited in claim 5 wherein the feedback to the user includes an indication that the volume of the user'"'"'s voice is too low.

7. The method as recited in claim 1 further comprising the step of forwarding the user to an operator when the identification of the at least one candidate as the intended recipient is not confirmed.

8. The method as recited in claim 1 further comprising the step of classifying the intended recipient into one or more classifications.

9. The method as recited in claim 8 wherein the one or more classifications include at least one of a department, a location, a title, a name, a yes or no response and a digit.

10. The method as recited in claim 1 further comprising the step of prompting the user to confirm the identification of the at least one candidate as the intended recipient.

11. The method as recited in claim 10 wherein the identification of the at least one candidate as the intended recipient is performed by depressing at least one number on a keypad of a telephone.

12. The method as recited in claim 1 wherein the analyzing step comprises the step of recognizing the input by using a predetermined grammar.

13. The method as recited in claim 1 wherein the input is analyzed using a speech recognition algorithm.

14. The method as recited in claim 1 wherein the predetermined vocabulary includes nicknames.

15. The method as recited in claim 1 further comprising the step of employing an adaptation method.

16. An automated conversational name dialing apparatus comprising:

a processing device having a processor and memory, the processor configured to analyze an input from a user, wherein the input comprises information directed to identifying an intended recipient of a telephone call from the user;

identify at least one candidate for the intended recipient, in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary;

determine a confidence measure indicative of a likelihood that the at least one candidate is the intended recipient; and

prompt the user for additional information to increase the likelihood that the at least one candidate is the intended recipient, wherein a prompt type is selectable from a group comprising two or more prompt types, each prompt type obtaining a specified type of additional information from the user, and selected in accordance with the determined confidence measure.

17. The apparatus as recited in claim 16 wherein the processor is configured to analyze native and non-native pronunciations of foreign names.

18. The apparatus as recited in claim 16 wherein the memory comprises a large vocabulary.

19. An article of manufacture for automated conversational name dialing, the article comprising a machine readable medium containing one or more programs which when executed implement the steps of:

analyzing an input from a user, wherein the input comprises information directed to identifying an intended recipient of a telephone call from the user;

identifying at least one candidate for the intended recipient, in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary;

determining a confidence measure indicative of a likelihood that the at least one candidate is the intended recipient; and

prompting the user for additional information to increase the likelihood that the at least one candidate is the intended recipient, wherein a prompt type is selectable from a group comprising two or more prompt types, each prompt type obtaining a specified type of additional information from the user, and selected in accordance with the determined confidence measure.