Gakuto Kurata  Gakuto Kurata photo         

contact information

Distinguished Engineer and Chief Scientist for Spoken Conversational Systems
IBM Research - Tokyo
  

links

Professional Associations

Professional Associations:  Acoustical Society of Japan  |  Association for Computational Linguistics  |  IEEE Signal Processing Society   |  IEEE, Senior Member  |  International Speech Communication Association (ISCA)  |  IPSJ


2018

Approach to reducing the response time of a speech interface
Kurata, Gakuto and Nagano, Tohru
US Patent App. 15/727,154
Abstract

Generating labeled data by sequence-to-sequence modeling with added perturbations to encoded information
Kurata, Gakuto
US Patent App. 15/236,197
Abstract

Recurrent neural network processing pooling operation
Kurata, Gakuto and Suzuki, Masayuki
US Patent App. 15/271,324
Abstract

Supervised training for word embedding
Kurata, Gakuto and Suzuki, Masayuki and Tachibana, Ryuki
US Patent App. 15/275,029
Abstract

Detecting customers with low speech recognition accuracy by investigating consistency of conversation in call-center
Kurata, Gakuto and Suzuki, Masayuki A
US Patent App. 15/823,074
Abstract

Neural network based acoustic models for speech recognition by grouping context-dependent targets
Kurata, Gakuto
US Patent App. 15/226,478
Abstract

Neural network for chemical compounds
Hara, Satoshi and Kurata, Gakuto and Nakagawa, Shigeru and Takeda, Seiji
US Patent App. 15/202,211
Abstract

Leveraging class information to initialize a neural network langauge model
Kurata, Gakuto
US Patent App. 15/249,872
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
Itoh, Nobuyasu and Kurata, Gakuto and Nishimura, Masafumi
US Patent 9,892,727
Abstract


2017

Training deep neural network for acoustic modeling in speech recognition
Kurata, Gakuto
US Patent 9,842,610
Abstract

Finding of a target document in a spoken language processing
Kurata, Gakuto and Suzuki, Masayuki A and Tachibana, Ryuki
US Patent App. 15/077,260
Abstract

Scheme of new materials
Hsu, Hsiang H and Kurata, Gakuto and Masuda, Koji and Nakagawa, Shigeru and Nakamura, Hajime and Takeda, Seiji
US Patent App. 14/984,989
Abstract

Adaptation of model for recognition processing
Kurata, Gakuto
US Patent App. 15/048,318
Abstract

Discriminative training of automatic speech recognition models with natural language processing dictionary for spoken language processing
Suzuki, Masayuki and Itoh, Nobuyasu and Kurata, Gakuto and Nagano, Tohru
US Patent App. 14/968,439
Abstract

Learning a model for recognition processing
Kurata, Gakuto
US Patent App. 14/815,564
Abstract

Method, system and computer program product for learning classification model
Kurata, Gakuto
US Patent App. 15/251,008
Abstract

Unsupervised training method for an N-gram language model based upon recognition reliability
Itoh, Nobuyasu and Kurata, Gakuto and Nishimura, Masafumi
US Patent 9,601,110
Abstract

Unsupervised training method, training apparatus, and training program for an N-gram language model based upon recognition reliability
Itoh, Nobuyasu and Kurata, Gakuto and Nishimura, Masafumi
US Patent 9,536,518
Abstract


2016

Correcting N-gram probabilities by page view information
Bodenstab, Nathan M and Itoh, Nobuyasu and Kurata, Gakuto and Nishimura, Masafumi and Vozila, Paul J
US Patent 9,251,135
Abstract

SPEECH RETRIEVAL METHOD, SPEECH RETRIEVAL APPARATUS, AND PROGRAM FOR SPEECH RETRIEVAL APPARATUS
T. Nagano, others
United States Patent 9373328

METHOD FOR IMPROVING ACOUSTIC MODEL, COMPUTER FOR IMPROVING ACOUSTIC MODEL AND COMPUTER PROGRAM THEREOF
T. Nagano, others
Japan Patent 5995226

SPEECH RECOGNITION MODEL CONSTRUCTION METHOD, SPEECH RECOGNITION METHOD, COMPUTER SYSTEM, SPEECH RECOGNITION APPARATUS, PROGRAM, AND RECORDING MEDIUM
T. Nagano, others
Japan Patent 6052814


2015

Information processing device, large vocabulary continuous speech recognition method and program including hypothesis ranking
Kurata, Gakuto and Suzuki, Masayuki and Nishimura, Masafumi
US Patent 9,165,553
Abstract

Building of n-gram language model for automatic speech recognition (asr)
Kurata, Gakuto and Nagano, Toru and Suzuki, Masayuki and Tachibana, Ryuki
US Patent App. 14/838,643
Abstract


2014


PRONUNCIATION ACCURACY IN SPEECH RECOGNITION
Gakuto Kurata, Masafumi Nishimura, Ryuki Tachibana
US Patent 20,140,358,533


2013



2012

SYSTEM FOR PROCESSING VOICE DATA IN CONVERSATION BETWEEN TWO PERSONS, AND METHOD AND PROGRAM PRODUCT
G. Kurata, M. Nishimura
Japan Patent 5088741

SEAMLESS INPUT METHOD FOR FREE KEYWORDS AND PHRASES BY USING THE LANGUAGE MODEL
N. Itoh, G. Kurata
Japan Patent 5068225




2011

SPEECH RECOGNITION SYSTEM AND METHOD
G. Kurata, N. Itoh, M. Nishimura
Japan Patent 4808764

SYSTEM AND METHOD FOR SUPPORTING TEXT-TO-SPEECH
G. Kurata, T. Nagano, M. Nishimura, R. Tachibana
US Patent 7,921,014


2010



2009




2008

SYSTEM FOR SUPPORTING TEXT-TO-SPEECH
M. Nishimura, G. Kurata, R. Tachibana
Japan Patent 4129989

APPARATUS, METHOD, AND PROGRAM FOR SUPPORTING SPEECH INTERFACE DESIGN
G. Kurata, O.Ichikawa, M. Nishimura
Japan Patent 4156639


2007