Patents by Inventor Maiko Hirahara

Maiko Hirahara has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 7949535
    Abstract: A system and method is provided for easily detecting a fraudulent user who attempts to obtain authentication using voice reproduced by a reproducer. A personal computer is provided with an audio data obtaining portion for picking up ambient sound around a person as a target of user authentication using voice authentication technology during a period before the person utters, and a fraud determination portion for calculating an intensity level showing intensity of the picked-up ambient sound per predetermined time for each of sections into which the period is divided and for determining that the person is a fraudulent user who attempts to obtain authentication using reproduced voice, when, of two of the calculated intensity levels, the intensity level of the later section is larger than a sum of the intensity level of the earlier section and a predetermined value.
    Type: Grant
    Filed: July 26, 2006
    Date of Patent: May 24, 2011
    Assignee: Fujitsu Limited
    Inventors: Toshiyuki Ohta, Maiko Hirahara, Kazunari Hirakawa
  • Publication number: 20070266154
    Abstract: A system and method is provided for easily detecting a fraudulent user who attempts to obtain authentication using voice reproduced by a reproducer. A personal computer is provided with an audio data obtaining portion for picking up ambient sound around a person as a target of user authentication using voice authentication technology during a period before the person utters, and a fraud determination portion for calculating an intensity level showing intensity of the picked-up ambient sound per predetermined time for each of sections into which the period is divided and for determining that the person is a fraudulent user who attempts to obtain authentication using reproduced voice, when, of two of the calculated intensity levels, the intensity level of the later section is larger than a sum of the intensity level of the earlier section and a predetermined value.
    Type: Application
    Filed: July 26, 2006
    Publication date: November 15, 2007
    Inventors: Toshiyuki Ohta, Maiko Hirahara, Kazunari Hirakawa