Patents by Inventor Gakuto Kurata

Gakuto Kurata 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).

  • Publication number: 20170061330
    Abstract: Method, system and computer program product for learning classification model. The present invention provides a computer-implemented method for learning a classification model using one or more training data each having a training input and one or more correct labels assigned to the training input, the classification model having a plurality of hidden units and a plurality of output units is provided. The method includes: obtaining a combination of co-occurring labels expected to be appeared together for an input to the classification model; initializing the classification model with preparing a dedicated unit for the combination from among the plurality of the hidden units so as to activate together related output units connected to the dedicated unit among the plurality of the output units, each related output unit corresponding to each co-occurring label in the combination; and training the classification model using the one or more training data.
    Type: Application
    Filed: August 30, 2016
    Publication date: March 2, 2017
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventor: GAKUTO KURATA
  • Patent number: 9583109
    Abstract: A dialog server which provides dialogs made by at least one user through their respective avatars in a virtual space. A method and a computer readable article of manufacture tangibly embodying computer readable instructions for executing the steps of the method are also provided. The dialog server includes: a position storage unit which stores positional information on the avatars; an utterance receiver which receives at least one utterance of avatars and utterance strength representing an importance or attention level of the utterance; an interest level calculator which calculates interest levels between avatars based on their positional information; a message processor which generates a message based on the utterance in accordance with a value calculated from the interest levels and the utterance strength; and a message transmitter which transmits the message to the avatars.
    Type: Grant
    Filed: October 7, 2013
    Date of Patent: February 28, 2017
    Assignee: Activision Publishing, Inc.
    Inventors: Gakuto Kurata, Tohru Nagano, Michiaki Tatsubori
  • Publication number: 20170032244
    Abstract: A method, system, and computer program product for learning a recognition model for recognition processing. The method includes preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label. The input segment and the additional segment are extracted from an original training data. A classification model is trained, using the input segment and the additional segment in the examples, to initialize parameters of the classification model so that extended segments including the input segment and the additional segment are reconstructed from the input segment. Then, the classification model is tuned to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters. At least a portion of the obtained classification model is included in the recognition model.
    Type: Application
    Filed: July 31, 2015
    Publication date: February 2, 2017
    Inventor: Gakuto Kurata
  • 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: 20160379665
    Abstract: A method is provided for training a Deep Neural Network (DNN) for acoustic modeling in speech recognition. The method includes reading central frames and side frames as input frames from a memory. The side frames are preceding side frames preceding the central frames and/or succeeding side frames succeeding the central frames. The method further includes executing pre-training for only the central frames or both the central frames and the side frames and fine-tuning for the central frames and the side frames so as to emphasize connections between acoustic features in the central frames and units of the bottom layer in hidden layer of the DNN.
    Type: Application
    Filed: June 26, 2015
    Publication date: December 29, 2016
    Inventor: Gakuto Kurata
  • 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
  • Publication number: 20160180836
    Abstract: Embodiments include methods and systems for improving an acoustic model. Aspects include acquiring a first standard deviation value by calculating standard deviation of a feature from first training data and acquiring a second standard deviation value by calculating standard deviation of a feature from second training data acquired in a different environment from an environment of the first training data. Aspects also include creating a feature adapted to an environment where the first training data is recorded, by multiplying the feature acquired from the second training data by a ratio obtained by dividing the first standard deviation value by the second standard deviation value. Aspects further include reconstructing an acoustic model constructed using training data acquired in the same environment as the environment of the first training data using the feature adapted to the environment where the first training data is recorded.
    Type: Application
    Filed: December 15, 2015
    Publication date: June 23, 2016
    Inventors: GAKUTO KURATA, TORU NAGANO, MASAYUKI SUZUKI
  • 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
  • Publication number: 20160155438
    Abstract: Embodiments include methods and systems for improving an acoustic model. Aspects include acquiring a first standard deviation value by calculating standard deviation of a feature from first training data and acquiring a second standard deviation value by calculating standard deviation of a feature from second training data acquired in a different environment from an environment of the first training data. Aspects also include creating a feature adapted to an environment where the first training data is recorded, by multiplying the feature acquired from the second training data by a ratio obtained by dividing the first standard deviation value by the second standard deviation value. Aspects further include reconstructing an acoustic model constructed using training data acquired in the same environment as the environment of the first training data using the feature adapted to the environment where the first training data is recorded.
    Type: Application
    Filed: October 28, 2015
    Publication date: June 2, 2016
    Inventors: GAKUTO KURATA, TORU NAGANO, MASAYUKI SUZUKI
  • 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
  • Publication number: 20160086599
    Abstract: A construction method for a speech recognition model, in which a computer system includes; a step of acquiring alignment between speech of each of a plurality of speakers and a transcript of the speaker; a step of joining transcripts of the respective ones of the plurality of speakers along a time axis, creating a transcript of speech of mixed speakers obtained from synthesized speech of the speakers, and replacing predetermined transcribed portions of the plurality of speakers overlapping on the time axis with a unit which represents a simultaneous speech segment; and a step of constructing at least one of an acoustic model and a language model which make up a speech recognition model, based on the transcript of the speech of the mixed speakers.
    Type: Application
    Filed: September 23, 2015
    Publication date: March 24, 2016
    Inventors: Gakuto Kurata, Toru Nagano, Masayuki Suzuki, Ryuki Tachibana
  • Patent number: 9269357
    Abstract: A system, method, and computer readable article of manufacture for extracting a specific situation in a conversation. The system includes: an acquisition unit for acquiring speech voice data of speakers in the conversation; a specific expression detection unit for detecting the speech voice data of a specific expression from speech voice data of a specific speaker in the conversation; and a specific situation extraction unit for extracting, from the speech voice data of the speakers in the conversation, a portion of the speech voice data that forms a speech pattern that includes the speech voice data of the specific expression detected by the specific expression detection unit.
    Type: Grant
    Filed: October 9, 2009
    Date of Patent: February 23, 2016
    Assignee: Nuance Communications, Inc.
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura
  • Patent number: 9251135
    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: August 13, 2013
    Date of Patent: February 2, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nathan M. Bodenstab, Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura, Paul J. Vozila
  • Publication number: 20160027433
    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: July 20, 2015
    Publication date: January 28, 2016
    Inventors: Nobuyasu Itoh, Gakuto Kurata, Masafumi Nishimura