Simulated voice message by concatenating voice files

摘要

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.