Patents by Inventor Takeshi Koya

Takeshi Koya 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).

  • Debugging assistance system and debugging assistance method
    Patent number: 12007872
    Abstract: A debug information abstraction unit (32) of a proxy server (30) adds, when a predetermined rule of an extension program is embodied into a program, a program for outputting debug information regarding the predetermined rule to the embodied program. Then, a debug information transmission unit (41b) of a terminal device (40) transmits, to a debug support device (10), the debug information regarding the predetermined rule for which the program has been added.
    Type: Grant
    Filed: January 17, 2020
    Date of Patent: June 11, 2024
    Assignee: Nippon Telegraph and Telephone Corporation
    Inventors: Hidetaka Koya, Hajime Nakajima, Takeshi Masuda
  • Method for recovering target speech based on amplitude distributions of separated signals
    Patent number: 7562013
    Abstract: The present invention provides a method for recovering target speech based on shapes of amplitude distributions of split spectra obtained by use of blind signal separation.
    Type: Grant
    Filed: August 31, 2004
    Date of Patent: July 14, 2009
    Assignee: Kitakyushu Foundation For The Advancement of Industry, Science and Technology
    Inventors: Hiromu Gotanda, Keiichi Kaneda, Takeshi Koya
  • Method for recovering target speech based on speech segment detection under a stationary noise
    Patent number: 7533017
    Abstract: Method for recovering target speech by extracting signal components falling in a speech segment, which is determined based on separated signals obtained through the Independent Component Analysis, thereby minimizing the residual noise in the recovered target speech.
    Type: Grant
    Filed: August 31, 2004
    Date of Patent: May 12, 2009
    Assignee: Kitakyushu Foundation for the Advancement of Industry, Science and Technology
    Inventors: Hiromu Gotanda, Keiichi Kaneda, Takeshi Koya
  • Recovering method of target speech based on split spectra using sound sources' locational information
    Patent number: 7315816
    Abstract: The present invention relates to a method for recovering target speech from mixed signals, which include the target speech and noise observed in a real-world environment, based on split spectra using sound sources' locational information.
    Type: Grant
    Filed: May 9, 2003
    Date of Patent: January 1, 2008
    Assignee: Zaidanhouzin Kitakyushu Sangyou Gakujutsu Suishin Kikou
    Inventors: Hiromu Gotanda, Kazuyuki Nobu, Takeshi Koya, Keiichi Kaneda, Takaaki Ishibashi
  • Method for recovering target speech based on amplitude distributions of separated signals
    Publication number: 20070100615
    Abstract: The present invention provides a method for recovering target speech based on shapes of amplitude distributions of split spectra obtained by use of blind signal separation.
    Type: Application
    Filed: August 31, 2004
    Publication date: May 3, 2007
    Inventors: Hiromu Gotanda, Keiichi Kaneda, Takeshi Koya
  • Method for recovering target speech based on speech segment detection under a stationary noise
    Publication number: 20070055511
    Abstract: Method for recovering target speech by extracting signal components falling in a speech segment, which is determined based on separated signals obtained through the Independent Component Analysis, thereby minimizing the residual noise in the recovered target speech.
    Type: Application
    Filed: August 31, 2004
    Publication date: March 8, 2007
    Inventors: Hiromu Gotanda, Keiichi Kaneda, Takeshi Koya
  • Recovering method of target speech based on split spectra using sound sources' locational information
    Publication number: 20040040621
    Abstract: The present invention relates to a method for recovering target speech from mixed signals, which include the target speech and noise observed in a real-world environment, based on split spectra using sound sources' locational information.
    Type: Application
    Filed: May 9, 2003
    Publication date: March 4, 2004
    Applicants: Zaidanhouzin Kitakyushu Sangyou Gakujutsu Suishin Kikou, Kabushikigaisha Wavecom, Kinki Daigaku
    Inventors: Hiromu Gotanda, Kazuyuki Nobu, Takeshi Koya, Keiichi Kaneda, Takaaki Ishibashi