System and method for the playing of key phrases in voice mail messages

• US 8,233,597 B2
• Filed: 02/11/2005
• Issued: 07/31/2012
• Est. Priority Date: 02/11/2005
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Kerr, Jim M., Chestnut, Kevin L.
• Primary Examiner(s): Phan, Joseph T
• Application Number:
  US11/057,333
• Publication Number:
  US 20060182232A1
• Time in Patent Office: 2,727 Days
• Field of Search: 379/88.01, 379 8823- 8825
• US Class Current: 379/88.22
• CPC Class Codes: H04M 3/53333 Message receiving aspects

Abstract

A method is provided for playing one or more key portions of a voice communication. The method includes storing, in a memory, a communication that includes one or more speech signals and a tag identifying a key portion of the one or more speech signals. The communication and the tag are retrieved from the memory. The key portion of the communication identified by the tag is played for a first end user.

Claims

1. A method for playing one or more key portions of a voice communication, comprising:

storing a communication comprising one or more speech signals in a memory;

using a speech recognition engine to scan the communication and identify a key portion of the one or more speech signals, the key portion comprising a series of patterns in the communication that are recognized by the speech recognition engine;

storing a tag identifying the key portion;

retrieving the communication and the tag from the memory;

in response to receiving a request to play the communication, playing the communication in its entirety for a first end user, wherein while playing the communication in its entirety the at least one key portion is played a first time for the first end user; and

after playing the communication in its entirety to the first end user and without requiring any further interaction from the first end user, automatically and immediately playing the key portion of the communication identified by the tag for a second time for the first end user such that the communication is not replayed in its entirety.

2. The method of claim 1, wherein the communication comprises a voice mail message.

3. The method of claim 2, wherein the key portion is selected from a group consisting of call back information, a number, a string of numbers, a date, or a time.

4. The method of claim 1, further comprising:

receiving the communication from a second end user;

scanning the communication to identify the key portion of the speech signals; and

associating the tag with the key portion of the speech signals.

5. The method of claim 4, wherein the communication is received from a non-IP telephony device in an analog format and the method further comprising:

converting the one or more speech signals from the analog format to a digital format to result in one or more digitized speech signals;

converting the digitized speech signals to a series of patterns; and

comparing the series of patterns to a set of stored modules to identify the key portion of the speech signals.

6. The method of claim 1, wherein storing the tag identifying the key portion comprises storing a starting position of the key portion of the speech signals within the communication.

7. The method of claim 6, wherein storing the tag identifying the key portion further comprises storing an ending position of the key portion of the speech signals within the communication.

8. The method of claim 6, wherein storing the tag identifying the key portion further comprises storing an amount of time associated with the key portion of the speech signals, the amount of time measured from the beginning of the key portion to the ending of the key portion.

10. The method of claim 1, further comprising:

receiving a command from the first end user; and

playing the key portion of the communication in response to receiving the command.

11. The method of claim 1, wherein playing the key portion of the communication comprises playing the key portion at a speed that is slower than a recorded speed.

25. The method of claim 1, further comprising:

in response to receiving the request to play the communication from the first end user and prior to playing the communication to the first end user, prompting the first end user to enter a command indicating that the first end user desires to hear the key portion of the message replayed the second time after the playing of the communication in its entirety; and

automatically playing the key portion of the communication identified by the tag the second time for the first end user in response to receiving the command.

9. A method for playing one or more key portions of a voice communication, comprising:

storing a communication comprising one or more speech signals in a memory;

using a speech recognition engine to scan the communication and identify a key portion of the one or more speech signals, the key portion comprising a series of patterns in the communication that are recognized by the speech recognition engine;

storing a tag identifying the key portion;

retrieving the communication and the tag from the memory;

playing only the key portion of the communication identified by the tag for a first end user such that the communication is not played in its entirety; and

after playing only the key portion of the communication to the first end user and without requiring any further interaction from the first end user, automatically and immediately playing the communication in its entirety for the first end user after playing only the key portion of the communication.

12. A system for playing one or more key portions of a voice communication, comprising:

a memory operable to store;

a communication comprising one or more speech signals; and

a tag identifying a key portion of the one or more speech signals; and

a processor in communication with the memory and operable to;

use a speech recognition engine to scan the communication and identify the key portion of the one or more speech signals, the key portion comprising a series of patterns in the communication that are recognized by the speech recognition engine;

tag key portion to identify the location of the key portion in the communication;

retrieve the communication and the tag from the memory;

in response to receiving a request to play the communication, play the communication in its entirety for a first end user, wherein while playing the communication in its entirety the at least one key portion is played a first time for the first end user; and

after playing the communication time to the first end user and without requiring any further interaction from the first end user, automatically and immediately play the key portion of the communication identified by the tag for a second time for the first end user such that the communication is not replayed in its entirety.

13. The system of claim 12, wherein the communication comprises a voice mail message.

14. The system of claim 13, wherein the key portion is selected from a group consisting of call back information, a number, a string of numbers, a date, or a time.

17. The system of claim 12, wherein the processor is further operable to store the tag identifying the key portion by storing a starting position of the key portion of the speech signals within the communication.

18. The system of claim 17, wherein the processor is further operable to store the tag identifying the key portion by storing an ending position of the key portion of the speech signals within the communication.

19. The system of claim 17, wherein the processor is further operable to store the tag identifying the key portion by storing an amount of time associated with the key portion of the speech signals, the amount of time measured from the beginning of the key portion to the ending of the key portion.

20. The system of claim 12, wherein the processor is further operable to play the communication in its entirety for a first end user after playing the key portion of the communication.

21. The system of claim 12, wherein the processor is further operable to:

receive a command from the first end user; and

play the key portion of the communication in response to receiving the command.

22. The system of claim 12, wherein the processor is further operable to play the key portion at a speed that is slower than a recorded speed.

26. The system of claim 12, wherein the processor is further operable to:

in response to receiving the request to play the communication from the first end user and prior to playing the communication to the first end user, prompt the first end user to enter a command indicating that the first end user desires to hear the key portion of the message replayed the second time after the playing of the communication in its entirety; and

automatically play the key portion of the communication identified by the tag the second time for the first end user in response to receiving the command.

15. A system for playing one or more key portions of a voice communication, comprising:

a memory operable to store;

a communication comprising one or more speech signals; and

a tag identifying a key portion of the one or more speech signals; and

a processor in communication with the memory and operable to;

receive the communication from a second end user;

scan the communication to identify the key portion of the speech signals;

associate the tag with the key portion of the speech signals;

retrieve the communication and the tag from the memory;

in response to receiving a request to play the communication, play the communication in its entirety for a first end user, wherein while playing the communication in its entirety the at least one key portion is played a first time for the first end user; and

after playing the communication in its entirety to the first end user and without requiring any further interaction from the first end user, automatically and immediately play the key portion of the communication identified by the tag for a second time for the first end user such that the communication is not replayed in its entirety.

16. The system of claim 15, wherein the communication is received from a non-IP telephony device in an analog format and wherein the processor is further operable to:

convert the one or more speech signals from the analog format to a digital format to result in one or more digitized speech signals;

convert the digitized speech signals to a series of patterns; and

compare the series of patterns to a set of stored modules to identify the key portion of the speech signals.

27. The system of claim 15, wherein the processor is further operable to:

in response to receiving the request to play the communication from the first end user and prior to playing the communication to the first end user, prompt the first end user to enter a command indicating that the first end user desires to hear the key portion of the message replayed the second time after the playing of the communication in its entirety; and

automatically play the key portion of the communication identified by the tag the second time for the first end user in response to receiving the command.

23. A system for playing one or more key portions of a voice communication, comprising:

means for storing a communication comprising one or more speech signals in a memory;

means for using a speech recognition engine to scan the communication and identify a key portion of the one or more speech signals, the key portion comprising a series of patterns in the communication that are recognized by the speech recognition engine;

means for storing a tag identifying the key portion;

means for retrieving the communication and the tag from the memory; and

in response to receiving a request to play the communication, means for playing the communication in its entirety for a first end user, wherein while playing the communication in its entirety the at least one key portion is played a first time for the first end user; and

after playing the communication in its entirety to the first end user and without requiring any further interaction from the first end user, means for automatically and immediately playing the key portion of the communication identified by the tag for a second time for the first end user such that the communication is not replayed in its entirety.

24. A tangible non-transitory machine-readable medium comprising logic operable to:

store a communication comprising one or more speech signals in a memory;

use a speech recognition engine to identify a key portion of the one or more speech signals, the key portion comprising a series of patterns in the communication that are recognized by the speech recognition engine;

store a tag identifying the key portion;

retrieve the communication and the tag from the memory;

in response to receiving a request to play the communication, play the communication in its entirety for a first end user, wherein while playing the communication in its entirety the at least one key portion is played a first time for the first end user; and

after playing the communication in its entirety to the first end user and without requiring any further interaction from the first end user, automatically and immediately play the key portion of the communication identified by the tag for a second time for the first end user such that the communication is not replayed in its entirety.

28. The tangible non-transitory machine-readable medium of claim 24, wherein the logic is further operable to:

in response to receiving the request to play the communication from the first end user and prior to playing the communication to the first end user, prompt the first end user to enter a command indicating that the first end user desires to hear the key portion of the message replayed the second time after the playing of the communication in its entirety; and

automatically play the key portion of the communication identified by the tag the second time for the first end user in response to receiving the command.