Patents by Inventor Masafumi Nishimura

Masafumi Nishimura 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: 10418029
    Abstract: Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods. The present invention provides for selecting training text for a language model that includes: generating a template for selecting training text from a corpus in a first domain according to generation techniques of: (i) replacing one or more words in a word string selected from the corpus in the first domain with a special symbol representing any word or word string, and adopting the word string after replacement as a template for selecting the training text; and/or (ii) adopting the word string selected from the corpus in the first domain as the template for selecting the training text; and selecting text covered by the template as the training text from a corpus in a second domain different from the first domain.
    Type: Grant
    Filed: November 30, 2017
    Date of Patent: September 17, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 10343867
    Abstract: A steel sheet shape control method includes, (A) setting a target correction shape of the steel sheet at a position of an electromagnet to a curved shape, (B) measuring a steel sheet shape when electromagnetic correction is performed, (C) calculating the steel sheet shape in a nozzle position based on the steel sheet shape, (D) repeating (B) and (C) by resetting the target correction shape to a curved shape having a smaller amount of warp, (E) when the amount of warp of the steel sheet shape at the position of the nozzle is less than the upper limit value, (F) calculating vibration of the steel sheet at the position of the nozzle, and (G) adjusting a control gain of the electromagnet until amplitude of vibration is less than a second upper limit value when the amplitude of the vibration is equal to or more than the second upper limit value.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: July 9, 2019
    Assignee: NIPPON STEEL CORPORATION
    Inventors: Yasushi Kurisu, Yoshihiro Yamada, Futoshi Nishimura, Katsuya Kojima, Junya Takahashi, Masaaki Omodaka, Masafumi Matsumoto, Hiroyuki Tanaka
  • Patent number: 9978364
    Abstract: A reading accuracy-improving system includes: a reading conversion unit for retrieving a plurality of candidate word strings from speech recognition results to determine the reading of each candidate word string; a reading score calculating unit for determining the speech recognition score for each of one or more candidate word strings with the same reading to determine a reading score; and a candidate word string selection unit for selecting a candidate to output from the plurality of candidate word strings on the basis of the reading score and speech recognition score corresponding to each candidate word string.
    Type: Grant
    Filed: March 28, 2016
    Date of Patent: May 22, 2018
    Assignee: International Business Machines Corporation
    Inventors: Gakuto Kurata, Masafumi Nishimura, Ryuki Tachibana
  • Publication number: 20180114524
    Abstract: Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods. The present invention provides for selecting training text for a language model that includes: generating a template for selecting training text from a corpus in a first domain according to generation techniques of: (i) replacing one or more words in a word string selected from the corpus in the first domain with a special symbol representing any word or word string, and adopting the word string after replacement as a template for selecting the training text; and/or (ii) adopting the word string selected from the corpus in the first domain as the template for selecting the training text; and selecting text covered by the template as the training text from a corpus in a second domain different from the first domain.
    Type: Application
    Filed: November 30, 2017
    Publication date: April 26, 2018
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9934776
    Abstract: Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods. The present invention provides for selecting training text for a language model that includes: generating a template for selecting training text from a corpus in a first domain according to generation techniques of: (i) replacing one or more words in a word string selected from the corpus in the first domain with a special symbol representing any word or word string, and adopting the word string after replacement as a template for selecting the training text; and/or (ii) adopting the word string selected from the corpus in the first domain as the template for selecting the training text; and selecting text covered by the template as the training text from a corpus in a second domain different from the first domain.
    Type: Grant
    Filed: July 20, 2015
    Date of Patent: April 3, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9892727
    Abstract: Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods. The present invention provides for selecting training text for a language model that includes: generating a template for selecting training text from a corpus in a first domain according to generation techniques of: (i) replacing one or more words in a word string selected from the corpus in the first domain with a special symbol representing any word or word string, and adopting the word string after replacement as a template for selecting the training text; and/or (ii) adopting the word string selected from the corpus in the first domain as the template for selecting the training text; and selecting text covered by the template as the training text from a corpus in a second domain different from the first domain.
    Type: Grant
    Filed: December 10, 2015
    Date of Patent: February 13, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9747893
    Abstract: A computer-based, unsupervised training method for an N-gram language model includes reading, by a computer, recognition results obtained as a result of speech recognition of speech data; acquiring, by the computer, a reliability for each of the read recognition results; referring, by the computer, to the recognition result and the acquired reliability to select an N-gram entry; and training, by the computer, the N-gram language model about selected one of more of the N-gram entries using all recognition results.
    Type: Grant
    Filed: October 6, 2016
    Date of Patent: August 29, 2017
    Assignee: International Business Machines Corporation
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9626958
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Grant
    Filed: May 27, 2016
    Date of Patent: April 18, 2017
    Assignee: SINOEAST CONCEPT LIMITED
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Patent number: 9626957
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Grant
    Filed: May 27, 2016
    Date of Patent: April 18, 2017
    Assignee: SINOEAST CONCEPT LIMITED
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Patent number: 9601110
    Abstract: A computer-based, unsupervised training method for an N-gram language model includes reading, by a computer, recognition results obtained as a result of speech recognition of speech data; acquiring, by the computer, a reliability for each of the read recognition results; referring, by the computer, to the recognition result and the acquired reliability to select an N-gram entry; and training, by the computer, the N-gram language model about selected one of more of the N-gram entries using all recognition results.
    Type: Grant
    Filed: June 24, 2015
    Date of Patent: March 21, 2017
    Assignee: International Business Machines Corporation
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Publication number: 20170025118
    Abstract: A computer-based, unsupervised training method for an N-gram language model includes reading, by a computer, recognition results obtained as a result of speech recognition of speech data; acquiring, by the computer, a reliability for each of the read recognition results; referring, by the computer, to the recognition result and the acquired reliability to select an N-gram entry; and training, by the computer, the N-gram language model about selected one of more of the N-gram entries using all recognition results.
    Type: Application
    Filed: October 6, 2016
    Publication date: January 26, 2017
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9536518
    Abstract: A computer-based, unsupervised training method for an N-gram language model includes reading, by a computer, recognition results obtained as a result of speech recognition of speech data; acquiring, by the computer, a reliability for each of the read recognition results; referring, by the computer, to the recognition result and the acquired reliability to select an N-gram entry; and training, by the computer, the N-gram language model about selected one of more of the N-gram entries using all recognition results.
    Type: Grant
    Filed: March 10, 2015
    Date of Patent: January 3, 2017
    Assignee: International Business Machines Corporation
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Publication number: 20160275939
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Application
    Filed: May 27, 2016
    Publication date: September 22, 2016
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Publication number: 20160275940
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Application
    Filed: May 27, 2016
    Publication date: September 22, 2016
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Publication number: 20160210964
    Abstract: A reading accuracy-improving system includes: a reading conversion unit for retrieving a plurality of candidate word strings from speech recognition results to determine the reading of each candidate word string; a reading score calculating unit for determining the speech recognition score for each of one or more candidate word strings with the same reading to determine a reading score; and a candidate word string selection unit for selecting a candidate to output from the plurality of candidate word strings on the basis of the reading score and speech recognition score corresponding to each candidate word string.
    Type: Application
    Filed: March 28, 2016
    Publication date: July 21, 2016
    Inventors: Gakuto Kurata, Masafumi Nishimura, Ryuki Tachibana
  • Patent number: 9384730
    Abstract: A reading accuracy-improving system includes: a reading conversion unit for retrieving a plurality of candidate word strings from speech recognition results to determine the reading of each candidate word string; a reading score calculating unit for determining the speech recognition score for each of one or more candidate word strings with the same reading to determine a reading score; and a candidate word string selection unit for selecting a candidate to output from the plurality of candidate word strings on the basis of the reading score and speech recognition score corresponding to each candidate word string.
    Type: Grant
    Filed: April 14, 2014
    Date of Patent: July 5, 2016
    Assignee: International Business Machines Corporation
    Inventors: Gakuto Kurata, Masafumi Nishimura, Ryuki Tachibana
  • Patent number: 9378736
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Grant
    Filed: April 21, 2015
    Date of Patent: June 28, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Patent number: 9373328
    Abstract: A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
    Type: Grant
    Filed: June 22, 2015
    Date of Patent: June 21, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Gakuto Kurata, Tohru Nagano, Masafumi Nishimura
  • Publication number: 20160163309
    Abstract: Method of selecting training text for language model, and method of training language model using the training text, and computer and computer program for executing the methods. The present invention provides for selecting training text for a language model that includes: generating a template for selecting training text from a corpus in a first domain according to generation techniques of: (i) replacing one or more words in a word string selected from the corpus in the first domain with a special symbol representing any word or word string, and adopting the word string after replacement as a template for selecting the training text; and/or (ii) adopting the word string selected from the corpus in the first domain as the template for selecting the training text; and selecting text covered by the template as the training text from a corpus in a second domain different from the first domain.
    Type: Application
    Filed: December 10, 2015
    Publication date: June 9, 2016
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9311291
    Abstract: Methods and a system for calculating N-gram probabilities in a language model. A method includes counting N-grams in each page of a plurality of pages or in each document of a plurality of documents to obtain respective N-gram counts therefor. The method further includes applying weights to the respective N-gram counts based on at least one of view counts and rankings to obtain weighted respective N-gram counts. The view counts and the rankings are determined with respect to the plurality of pages or the plurality of documents. The method also includes merging the weighted respective N-gram counts to obtain merged weighted respective N-gram counts for the plurality of pages or the plurality of documents. The method additionally includes calculating a respective probability for each of the N-grams based on the merged weighted respective N-gram counts.
    Type: Grant
    Filed: September 9, 2013
    Date of Patent: April 12, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nathan M. Bodenstab, Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura, Paul J. Vozila