Simulated voice message by concatenating voice files

• US 20050254631A1
• Filed: 05/13/2004
• Published: 11/17/2005
• Est. Priority Date: 05/13/2004
• Status: Active Grant

• Current Assignee: Extended Data Solutions, Inc.
• Original Assignee: Extended Data Solutions, Inc.
• Inventors: Smith, Scott R., O'Hara, James E., Kipp, Brian C.
• Granted Patent: US 7,206,390 B2
• Time in Patent Office: Days
• US Class Current: 379/88.10
• CPC Class Codes: H04L 12/64 Hybrid switching systems
• CPC Class Codes: H04M 1/645 with speech synthesis

Abstract

Computer-generated personalized voice messages are created by concatenating data files of audio that were pre-recorded in the voice of an individual whose live voice is to be simulated during the delivery of the voice message. A call to a person or list of persons is placed by a computer. Common identifiers of each person to be called are read from a data base of data files, and matched with a separate data base containing recorded voice phrases, each of which is a digitization of the individual speaking content corresponding to the identifier—such as the person'"'"'s first name. The recorded voice phrase audio is concatenated with at least one other audio file, which is a digitization of a message to be delivered to the called person.

Claims

1. A method of automatically delivering a telephone message to a first person in the voice of a second person by concatenating digital files, the contents of which are digital representations of the second person'"'"'s voice, such that an audio signal is produced from the concatenated files, which impersonates the second person speaking to the first person, the method comprising:

obtaining at least one identifier of a first person from a data base;

obtaining a phone number for the first person from a data base;

obtaining from a data base, a first data file, the contents of which is a digitization of the second person speaking content corresponding to the identifier of the first person;

automatically originating a telephone call from a computer, to the phone number for the first person;

detecting by a computer, the telephone call as being answered, and

after the telephone call is answered, transmitting to the called number, an analog signal generated by a computer, by concatenating the first data file and a second data file and generating an audio signal from the concatenated data files, the second data file being a digitization of a voice message to be conveyed to the first person, the concatenated data files being digitized speech of the second person such that the audio signal generated from the concatenated files is substantially identical to the second person'"'"'s voice and impersonates the second person speaking to the first person.

2. The method of claim 1 wherein the step of obtaining an identifier of a first person from a data base, includes the step of obtaining a person'"'"'s name from a data base.

3. The method of claim 1 wherein the identifier is a reoccurring identifier for a plurality of persons.

4. The method of claim 1 wherein the identifier is at least one of:

a common name;

a demographic characteristic;

a political party affiliation or membership;

affiliation with a particular religion;

a voting history;

a geographic area;

an affiliation with or to an organization, corporation or group;

a purchase of a particular product or service; and

a known interest or hobby;

5. The method of claim 2 wherein the step of determining a name includes the step of determining the name to be a common name.

6. The method of claim 5 wherein the common name is a common first name.

7. The method of claim 5 wherein the common name is a common surname.

8. The method of claim 6 wherein the step of transmitting an analog signal includes the step of generating an analog electrical signal that produces audio at the called number that includes the common first name.

9. The method of claim 7 wherein the step of transmitting an analog signal includes the step of generating an analog electrical signal that produces audio at the called number that includes the common surname.

10. The method of claim 1 wherein the step of generating an analog signal by a computer, includes the step of:

concatenating data files of digitized speech according to predetermined rules on how the identifier should be rendered as speech of the second person.

11. The method of claim 1 wherein the step of, transmitting to the called number, an analog signal generated by a computer from at least first and second concatenated data files, includes the step of concatenating a digitized speech file that represents the second person enunciating a salutation.

12. The method of claim 1 wherein the second data file is comprised of a plurality of dropped in data files.

13. The method of claim 1 including a step wherein the second data file is selected from a plurality of files, each of which produces a different audio signal that conveys different content.

14. The method of claim 1 wherein automatically originating a telephone call from a computer includes originating a call to a plurality of phone numbers substantially simultaneously and wherein the step of transmitting to the called number, an analog signal includes the step of transmitting the analog signal to a plurality of the called numbers that answered.

15. The method of claim 1 wherein the second person is a candidate for political office.

16. The method of claim 15 wherein at least one of the first and second concatenated data files is a digitization of a political message, spoken by a political candidate, such that the audio electrical signal produced at the called phone number by the concatenated data files replicates the voice of the political candidate speaking to the first person.

17. The method of claim 15 wherein at least one of the first and second concatenated data files is a digitization of a political message spoken using a voice that impersonates the voice of a political candidate such that the audio electrical signal produced at the called phone number by the concatenated data files substantially replicates the voice of the political candidate, speaking to the first person.

18. The method of claim 1 wherein the second person is a celebrity.

19. The method of claim 18 wherein at least one of the first and second concatenated data files is a digitization of a commercial message, spoken by the celebrity, such that the audio electrical signal produced at the called phone number by the concatenated data files replicates the voice of the celebrity speaking to the first person.

20. The method of claim 16 wherein at least one of the first and second concatenated data files is a digitization of a commercial message spoken using a voice that impersonates the voice of the celebrity such that the audio electrical signal produced at the called phone number by the concatenated data files substantially replicates the voice of the celebrity, speaking to the first person.

21. The method of claim 1 wherein the concatenated data files are WAV files.

22. The method of claim 1 wherein the step of automatically originating a telephone call from a computer includes the step of obtaining a phone number of a first person from the data base of persons.

23. The method of claim 1 wherein the first data base of persons is a data base of voters.

25. The method of claim 1 wherein the data base of persons is a data base of prospective customers.

26. The method of claim 1 wherein the step of automatically originating a telephone call includes placing a telephone call using cellular or other wireless communication service.

27. The method of claim 1 wherein the step of automatically originating a telephone call includes the step of placing a telephone call using Voice Over Internet Protocol

28. The method of claim 1 wherein the step of automatically originating a telephone call includes placing the call at a time of day the telephone call is expected to be directed to a voice recording device.

29. An apparatus for delivering a telephone message to a first person in the voice of a second person comprising:

a computer that is operatively coupled to;

a) a first data base having identifying characteristics of at least a first person and a phone number associated with the first person;

b) a second data base of digital audio files, each digital audio file being a digitization of the second person speaking phrases associated with the identifying characteristics of the first person;

c) a communication network;

d) a third data base, storing at least one second audio file, which is a digitization of a voice message, spoken by the second person; and

e) memory, storing computer program instructions, which when they are executed, cause the computer to;

i) obtain a first telephone number of a first person, from the first data base

ii) determine if there is a digitization of the phrases associated with the identifying characteristics of the first person;

iii) if there is a digitization of the phrases associated with the identifying characteristics of the first person, then concatenate the first digital audio file with the second audio file;

v) place a call to the first telephone number;

vi) when the call is answered, generate a voice message from the first digital audio file and the second audio file to produce a voice message that sounds as if it is spoken by the second person and addressing the first person directly.