Patents by Inventor Yasuhiro Minami

Yasuhiro Minami 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: 10311888
    Abstract: A voice conversion device includes: a parameter learning unit in which a probabilistic model that uses speech information, speaker information, and phonological information as variables to thereby express relationships among binding energies between any two of the speech information, the speaker information and the phonological information by parameters is prepared, wherein the speech information is obtained based on a speech, the speaker information corresponds to the speech information, and the phonological information expresses the phoneme of the speech, and in which the parameters are determined by performing learning by sequentially inputting the speech information and the speaker information into the probabilistic model; and a voice conversion processing unit that performs voice conversion processing of the speech information obtained on the basis of the speech of an input speaker, based both on the parameters determined by the parameter learning unit and on the speaker information of a target speaker.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: June 4, 2019
    Assignee: THE UNIVERSITY OF ELECTRO-COMMUNICATIONS
    Inventors: Toru Nakashika, Yasuhiro Minami
  • Publication number: 20190051314
    Abstract: A voice conversion device includes: a parameter learning unit in which a probabilistic model that uses speech information, speaker information, and phonological information as variables to thereby express relationships among binding energies between any two of the speech information, the speaker information and the phonological information by parameters is prepared, wherein the speech information is obtained based on a speech, the speaker information corresponds to the speech information, and the phonological information expresses the phoneme of the speech, and in which the parameters are determined by performing learning by sequentially inputting the speech information and the speaker information into the probabilistic model; and a voice conversion processing unit that performs voice conversion processing of the speech information obtained on the basis of the speech of an input speaker, based both on the parameters determined by the parameter learning unit and on the speaker information of a target speaker.
    Type: Application
    Filed: February 22, 2017
    Publication date: February 14, 2019
    Applicant: THE UNIVERSITY OF ELECTRO-COMMUNICATIONS
    Inventors: Toru NAKASHIKA, Yasuhiro MINAMI
  • Patent number: 6672580
    Abstract: A sheet feeding apparatus comprises a pressure plate disposed at a position where sheets first hit the same and a separation plate for separating the sheets. The pressure plate and the separation plate are rotatable independently of each other. The pressure plate is pressed by one spring, while the separation plate is pressed by another spring, against sheet feed roller independently of each other.
    Type: Grant
    Filed: August 30, 2002
    Date of Patent: January 6, 2004
    Assignee: Matsushita Electric Industrial Co., Ltd.
    Inventors: Hiroshi Shibata, Yoshihiro Tsumori, Yasuhiro Minami, Keisuke Fujimaru
  • Publication number: 20030062668
    Abstract: With an aim to provide a sheet feeding apparatus in which multi-picking of sheets by the sheet feed roller is obviated even when stacked sheets are inserted with a rush, the invention comprises pressure plate 4 disposed at a position where sheets first hit the same and separation plate 60 for separating sheets, both of which are rotatable independently of each other. Pressure plate 4 is pressed by spring 50, while separation plate 60 is pressed by spring 70, against sheet feed roller 3 independently of each other.
    Type: Application
    Filed: August 30, 2002
    Publication date: April 3, 2003
    Inventors: Hiroshi Shibata, Yoshihiro Tsumori, Yasuhiro Minami, Keisuke Fujimaru
  • Patent number: 5721808
    Abstract: Noise-resistant speech HMMs are composed by: recording noise in the environment of utterance (S.sub.1); preparing HMMs of the noise (S.sub.2); transforming the output probability distribution of each of the noise HMMs and speech HMMs prepared from speech unaffected by noise and multiplicative distortion to a linear spectral domain (S.sub.31); multiplying the speech HMM distribution in the linear spectral domain by a multiplicative distortion W that is an unknown variable (S.sub.321); convoluting the multiplied value and the noise HMM distribution in the linear spectral domain (S.sub.322); inversely transforming the convoluted value to the original domain of the speech HMM (S.sub.33) to compose incomplete noise-resistant speech HMMs each containing multiplicative distortion as an unknown variable (S.sub.
    Type: Grant
    Filed: March 4, 1996
    Date of Patent: February 24, 1998
    Assignee: Nippon Telegraph and Telephone Corporation
    Inventors: Yasuhiro Minami, Tomoko Matsui, Sadaoki Furui
  • Patent number: D539842
    Type: Grant
    Filed: September 13, 2006
    Date of Patent: April 3, 2007
    Assignee: Matsushita Electric Industrial Co., Ltd.
    Inventors: Yasuhiro Minami, Junichi Tanizaki, Yoshihiro Mizoguchi