Interactive voice message retrieval

• US 7,738,637 B2
• Filed: 07/24/2004
• Issued: 06/15/2010
• Est. Priority Date: 07/24/2004
• Status: Active Grant

• Current Assignee: Massachusetts Institute of Technology
• Original Assignee: Massachusetts Institute of Technology
• Inventors: Marmasse, Natalia, Lakshmipathy, Vidya, Schmandt, Christopher
• Primary Examiner(s): Gauthier; Gerald
• Application Number:
  US10/897,709
• Publication Number:
  US 20060018446A1
• Time in Patent Office: 2,152 Days
• Field of Search: 379/76, 379/88.18, 379/88.23, 379/29.02, 379/88.1, 379/88.26, 379/88.17, 379/88.22, 379/202.01, 455/412.1, 704/249, 704/251, 704/270, 704/270.1, 709/233
• US Class Current: 379/88.17
• CPC Class Codes: H04M 1/6505 storing speech in digital form
• CPC Class Codes: H04M 1/72433 for voice messaging, e.g. dictaphones for answering incoming calls H04M1/64
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/53333 Message receiving aspects
• CPC Class Codes: H04M 3/53383 Message registering commands or announcements; Greetings

Abstract

A method for exchanging voice messages that may be employed in an answering machine, in wired or wireless telephone, or in an voice messaging system. An incoming voice message from a message source is received and recorded, parsed into segments, and the parsed message is played back to a listener, pausing between each of the parsed segments to accept and record a spoken response from the listener. A reply message is returned to the original message source that includes each such spoken response along with a snippet extracted from the particular segment responded to in the original message. The listener may also interrupt the playback of the voice message at any time to record a response.

Claims

1. A method for exchanging voice messages between a calling party and a called party comprising, in combination, the steps of:

receiving and recording an incoming voice message from said calling a party as a speech signal recording,

analyzing the voice signal content of said speech signal recording to identify boundaries subdividing said speech signal recording into segments,

reproducing said speech signal recording to said called party while pausing between at least some said segments to accept and record a spoken response from said called party as a recorded speech signal response, and

transmitting a reply message including each such recorded speech signal response to said calling party.

2. A method for exchanging voice messages as set forth in claim 1 wherein said step of analyzing the voice signal content of said speech signal recording comprises the step of detecting segment-delimiting pauses in said voice signal content.

3. A method for exchanging voice messages as set forth in claim 2 wherein said step of detecting segment-delimiting pauses includes the step of detecting the presence of intervals in said voice signal content having a low average magnitude.

4. A method for exchanging voice messages as set forth in claim 3 wherein said intervals of low average magnitude are preceded by an abrupt reduction in the average magnitude of said voice signal content and followed by an abrupt increase in the average magnitude of said voice signal content.

5. A method for exchanging voice messages as set forth in claim 3 wherein said step of detecting segment delimiting pauses includes the step of detecting the presence of single syllables in said voice signal content having a duration which exceeds a predetermined threshold duration.

6. A method for exchanging voice messages as set forth in claim 3 wherein said step of detecting the presence of intervals in said voice signal content having a low average magnitude comprises detecting intervals in said voice signal content having an average magnitude less than a predetermined threshold magnitude.

7. A method for exchanging voice messages as set forth in claim 2 wherein said step of detecting segment delimiting pauses includes the step of detecting the presence of single syllables in said voice signal content having an extended duration.

8. A method for exchanging voice messages as set forth in claim 2 wherein said step of detecting segment delimiting pauses includes the step of detecting the presence of intervals in said voice signal content having a low average magnitude and the presence of single syllables of extended duration in said voice signal content.

9. A method for exchanging voice messages as set forth in claim 1 further comprising the step performed at any time during the reproduction of said speech signal recording of accepting an interrupt command from said called party and thereafter recording said spoken response from said called party as a recorded speech signal response.

10. A method for exchanging voice messages as set forth in claim 9 wherein said step of detecting segment-delimiting pauses includes the step of detecting the presence of intervals in said voice signal content having a low average magnitude.

11. A method for exchanging voice messages as set forth in claim 9 wherein said step of detecting segment-delimiting pauses includes the step of detecting the presence of intervals in said voice signal content having a low average magnitude and the presence of single syllables of extended duration in said voice signal content.

12. A method for exchanging voice messages as set forth in claim 9 wherein said reply message comprises the combination of each such response and at least a portion of that segment of said speech signal recording reproduced immediately before the recording of each such spoken response.

13. A method for exchanging voice messages as set forth in claim 1 wherein said reply message comprises the combination of each such recorded speech signal response and at least a portion of that segment of said speech signal recording reproduced immediately before the recording of each such recorded speech signal response.

14. A method for exchanging voice messages as set forth in claim 13 wherein said portion of that segment of said speech signal recording reproduced immediately before the recording of each such recorded speech signal response has a predetermined maximum duration.

15. A method for exchanging voice messages as set forth in claim 14 wherein said portion of that segment of said speech signal recording reproduced immediately before the recording of each such recorded speech signal response is time compressed to reduce its duration while preserving its information content.

16. A method for exchanging voice messages as set forth in claim 13 wherein said reply message further includes pauses following each such recorded speech signal response.

17. A method for exchanging voice messages as set forth in claim 13 further comprising the step performed during the reproduction of said speech signal recording of accepting an interrupt command followed by recording a recorded speech signal response from said called party.

18. A method for exchanging voice messages as set forth in claim 1 wherein said step of transmitting a reply message to said calling party comprises establishing a telephone connection to said calling party and transmitting said reply message via said telephone connection.

19. A method for exchanging voice messages as set forth in claim 1 wherein said step of transmitting a reply message to said calling party comprises establishing an Internet connection to said calling party and transmitting said reply message via said Internet connection.

20. A method for exchanging voice messages as set forth in claim 1 wherein said step of transmitting a reply message to said calling party comprises transmitting said reply message as a part of an email message to said calling party.