Automated detection of spoken numbers in voice messages

• US 8,265,934 B2
• Filed: 04/08/2008
• Issued: 09/11/2012
• Est. Priority Date: 01/27/2000
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bates, Cary Lee, Day, Paul Reuben, Santosuosso, John Matthew
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US12/099,392
• Publication Number:
  US 20080187110A1
• Time in Patent Office: 1,617 Days
• Field of Search: 704/270, 704/246, 704/251, 379/88.08, 379/85
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An apparatus and program product utilize voice recognition to process voice messages in an automated manner to detect spoken numbers contained therein. Detected spoken numbers can then be utilized to set a start position at which to begin playback of a voice message, e.g., to permit a user to locate and transcribe a telephone number spoken by a message sender. Automated number detection may also be utilized to automatically dial telephone numbers mentioned in a voice message, as well as in the display of textual representations of such numbers to a user.

Claims

1. An apparatus, comprising:

a processor configured to execute a program to perform voice recognition on at least a portion of a voice message to generate a textual representation of the voice message, to detect a position of a spoken number in the textual representation of the voice message, to determine a playback start position based upon the position of the spoken number, to play the voice message starting at the playback start position, to receive user input to find a next number from a current playback position in the voice message, and to find the next number by searching for a closest subsequent entry in the textual representation from the current playback position that corresponds to a number.

2. The apparatus of claim 1, wherein the spoken number includes a plurality of spoken digits, and wherein the program is configured to detect the position of the spoken number by detecting a start position of a leading digit in the plurality of spoken digits.

3. The apparatus of claim 1, wherein the program is configured to determine the playback start position by setting the playback start position to a position earlier than the position of the spoken number.

4. The apparatus of claim 1, wherein the program is further configured to receive user input to find a previous number from a current playback position in the voice message, and wherein the program is configured to detect the position of the spoken number by detecting an immediately preceding spoken number from the current playback position.

5. The apparatus of claim 1, wherein the program is further configured to display at least a portion of the textual representation to a user.

6. The apparatus of claim 1, wherein the program is further configured to automatically dial the spoken number.

7. The apparatus of claim 6, wherein the program is configured to automatically dial the spoken number in response to user input.

8. The apparatus of claim 1, wherein the program is configured to detect whether the spoken number is a telephone number.

9. A program product, comprising:

a program comprising a plurality of instructions that, when executed, perform voice recognition on at least a portion of a voice message to generate a textual representation of the voice message, detect a position of a spoken number in the textual representation of the voice message, determine a playback start position based upon the position of the spoken number, detect whether the spoken number is a telephone number, play the voice message starting at the playback start position, receive user input to find a next number from a current playback position in the voice message, and find the next number by searching for a closest subsequent entry in the textual representation from the current playback position that corresponds to a number; and

a physical computer readable medium storing the program.

10. The program product of claim 9, wherein the computer readable medium includes a recordable medium.

11. The program product of claim 9, wherein the program further comprises at least one instruction that, when executed, detects the position of the spoken number by detecting an immediately preceding spoken number from the current playback position in response to user input to find a previous number from a current playback position in the voice message.

12. The program product of claim 9, wherein the program further comprises at least one instruction that, when executed, displays at least a portion of the textual representation to a user.

13. A method, comprising:

performing voice recognition on at least a portion of a voice message to generate a textual representation of the voice message;

detecting a position of a spoken number in the textual representation of the voice message;

determining a playback start position based upon the position of the spoken number;

playing the voice message starting at the playback start position;

receiving user input to find a next number from a current playback position in the voice message; and

using a processor, finding the next number by searching for a closest subsequent entry in the textual representation from the current playback position that corresponds to a number.

14. The method of claim 13, wherein the spoken number includes a plurality of spoken digits, and wherein the position of the spoken number is detected by detecting a start position of a leading digit in the plurality of spoken digits.

15. The method of claim 13, wherein the playback start position is determined by setting the playback start position to a position earlier than the position of the spoken number.

16. The method of claim 13, further comprising:

receiving user input to find a previous number from a current playback position in the voice message; and

detecting the previous number by detecting an immediately preceding spoken number from the current playback position.

17. The method of claim 13, further comprising:

displaying at least a portion of the textual representation to a user.

18. The method of claim 13, further comprising:

automatically dialing the spoken number.

19. The method of claim 18, wherein the spoken number is automatically dialed in response to user input.

20. The method of claim 13, further comprising:

detecting whether the spoken number is a telephone number.