Apparatus and method for providing call return service

• US 6,788,767 B2
• Filed: 12/28/2000
• Issued: 09/07/2004
• Est. Priority Date: 12/28/2000
• Status: Active Grant

• Current Assignee: Gateway Incorporated (Acer, Inc.)
• Original Assignee: Gateway Incorporated (Acer, Inc.)
• Inventors: Lambke, Jay V.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): ELAHEE, MD S
• Application Number:
  US09/754,049
• Publication Number:
  US 20020085688A1
• Time in Patent Office: 1,349 Days
• Field of Search: 379/88.01, 379/76, 379/88.14, 379/281, 379/387.02, 379/67.1, 379/88.24, 704/238, 704/241, 704/236, 704/232, 704/254, 704/255, 704/256, 704/257, 704/251, 704/234, 704/500, 455/413, 455/422, 709/246
• US Class Current: 379/88.01
• CPC Class Codes: H04M 1/6505 storing speech in digital form

Abstract

An apparatus and method for enabling provision of a call return service is disclosed. The apparatus utilizes a method of generating telephone numbers from voice messages. The method includes the step of using speech recognition to isolate a spoken number in a voice message, and confirming to a high degree of accuracy that the spoken number represents a telephone number. The method further includes the step of converting the spoken number into a data sequence representing the telephone number. This data sequence is then made available for immediate or later use.

Claims

1. A method of enabling provision of a communications service comprising:

receiving a command;

selecting a voice message, the selecting step including tracking a message content, thereby establishing a current message and identifying the current message as the voice message when the command is received in the receiving a command step;

isolating a spoken number in the voice message using speech recognition;

identifying a tag in the voice message; and

checking a syllabic distance between the tag and the spoken number, thereby using said distance for determining probability if the spoken number represents a telephone number;

converting the spoken number into a data sequence representing the spoken number; and

initiating provision of a communication service using the spoken number, the communication service being based upon the command.

2. The method of claim 1, wherein the tag is at least one spoken word.

3. The method of claim 2, wherein the identifying a tag step further comprises:

identifying a first spoken word;

identifying a second spoken word; and

checking a syllabic distance between the first spoken word and the second spoken word.

4. The method of claim 1, wherein the tag is a dual tone multi-frequency signal.

5. The method of claim 1, further comprising comparing the data sequence with known telephone number patterns, thereby enabling confirmation that the spoken number represents a telephone number.

6. The method of claim 1, wherein the command is a verbal callback command, and wherein the initiating step comprises dialing a telephone number represented by the data sequence.

7. The method of claim 6, wherein the data sequence is a dual tone multi-frequency signal.

8. The method of claim 1, wherein the command is a verbal store command, and wherein the initiating step comprises causing storage of the data sequence in a user directory.

9. The method of claim 1, wherein the receiving a command step comprises:

monitoring a voice input; and

processing the voice input using speech recognition, thereby identifying the command.

10. The method of claim 9, wherein the processing the voice input step comprises enabling the command to reference an alternate message, and wherein the selecting step comprises identifying the alternate message as the voice message when the alternate message is referenced by the command.

11. The method of claim 1, further comprising checking for a stored caller ID signal associated with the voice message.

12. A method of generating telephone numbers from voice messages for use with a calling apparatus, comprising:

using speech recognition to isolate a spoken number in a voice message, wherein using the speech recognition step utilizes speaker-independent speech recognition;

confirming that the spoken number represents a telephone number, said confirming step including identifying a tag in the voice message checking syllabic distance between the tag and the spoken number, thereby using said distance for determining probability if the spoken number represents a telephone number;

converting the spoken number into a data sequence representing the telephone number; and

checking for a stored caller ID signal associated with the voice message, if a stored caller ID signal is present, comparing said spoken number with said stored caller ID signal.

13. The method of claim 12, wherein the tag is at least one spoken word.

14. The method of claim 13, wherein the identifying a tag step further comprises:

identifying a first spoken word;

identifying a second spoken word; and

checking the syllabic distance between the first spoken word and the second spoken word, thereby confirming the identification of at least one spoken word.

15. The method of claim 12, wherein the tag is a dual tone multi-frequency signal.

16. The method of claim 12, wherein the confirming step comprises comparing the data sequence with known telephone number patterns.

17. The method of claim 16, wherein the data sequence is a dual tone multi-frequency signal.

18. A device for enabling provision of a communication service upon receipt of a given command, based upon information contained within a voice message, comprising:

means for using speech recognition to isolate a spoken number in the voice message;

means for confirming that the spoken number represents a telephone number, said confirming means including;

means for identifying a tag in the voice message;

means for checking a syllabic distance between the tag and the spoken number, thereby using said distance for determining probability if the spoken number represents a telephone number; and

means for comparing the data sequence with known telephone number patterns;

means for converting the spoken number into a data sequence representing the telephone number;

means for checking for a stored caller ID signal associated with the voice message, if a stored caller ID signal is present, comparing said spoken number with said stored caller ID signal; and

means for providing a communication service using the data sequence.

19. The device for claim 18, wherein the tag is at least one spoken word.

20. The device of claim 18, wherein the tag is a dual tone multi-frequency signal.