P

Inventor

KURATA GAKUTO

JP96 patents
⚠️ This page may combine multiple inventors who share the name “KURATA GAKUTO”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

IBM

42 patents
US10607604B2Mar 31, 2020

Method for re-aligning corpus and improving the consistency

IBM8 citations84
US10529318B2Jan 7, 2020

Implementing a classification model for recognition processing

IBM7 citations84
US10140983B2Nov 27, 2018

Building of n-gram language model for automatic speech recognition (ASR)

IBM7 citations84
US9536518B2Jan 3, 2017

Unsupervised training method, training apparatus, and training program for an N-gram language model based upon recognition reliability

IBM11 citations84
US10366779B2Jul 30, 2019

Scheme of new materials

IBM14 citations83
US9870765B2Jan 16, 2018

Detecting customers with low speech recognition accuracy by investigating consistency of conversation in call-center

IBM6 citations82
US11934938B2Mar 19, 2024

Neural network for chemical compounds

IBM3 citations75
US11443169B2Sep 13, 2022

Adaptation of model for recognition processing

IBM2 citations73
US11276391B2Mar 15, 2022

Generation of matched corpus for language model training

IBM2 citations73
US11263516B2Mar 1, 2022

Neural network based acoustic models for speech recognition by grouping context-dependent targets

IBM2 citations73
US11195513B2Dec 7, 2021

Generating phonemes of loan words using two converters

IBM2 citations73
US11157829B2Oct 26, 2021

Method to leverage similarity and hierarchy of documents in NN training

IBM2 citations73
US10915808B2Feb 9, 2021

Neural network for chemical compounds

IBM3 citations73
US10726828B2Jul 28, 2020

Generation of voice data as data augmentation for acoustic model training

IBM3 citations73
US10621509B2Apr 14, 2020

Method, system and computer program product for learning classification model

IBM5 citations73
US10572586B2Feb 25, 2020

Technique for automatically splitting words

IBM2 citations73
US10503827B2Dec 10, 2019

Supervised training for word embedding

IBM4 citations73
US10418029B2Sep 17, 2019

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

IBM1 citations73
US9934776B2Apr 3, 2018

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

IBM2 citations73
US9892727B2Feb 13, 2018

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

IBM2 citations73
US9812122B2Nov 7, 2017

Speech recognition model construction method, speech recognition method, computer system, speech recognition apparatus, program, and recording medium

IBM3 citations73
US11908454B2Feb 20, 2024

Integrating text inputs for training and adapting neural network transducer ASR models

IBM2 citations72
US11783811B2Oct 10, 2023

Accuracy of streaming RNN transducer

IBM3 citations72
US10089978B2Oct 2, 2018

Detecting customers with low speech recognition accuracy by investigating consistency of conversation in call-center

IBM4 citations71
US12367863B2Jul 22, 2025

External language model information integrated into neural transducer model

IBM0 citations63
US11893983B2Feb 6, 2024

Adding words to a prefix tree for improving speech recognition

IBM0 citations63
US11610108B2Mar 21, 2023

Training of student neural network with switched teacher neural networks

IBM0 citations63
US11610581B2Mar 21, 2023

Multi-step linear interpolation of language models

IBM0 citations63
US11574181B2Feb 7, 2023

Fusion of neural networks

IBM0 citations63
US11557288B2Jan 17, 2023

Hindrance speech portion detection using time stamps

IBM0 citations63
US11276394B2Mar 15, 2022

Method for re-aligning corpus and improving the consistency

IBM0 citations63
US11227579B2Jan 18, 2022

Data augmentation by frame insertion for speech data

IBM1 citations63
US11011161B2May 18, 2021

RNNLM-based generation of templates for class-based text generation

IBM0 citations63
US11011156B2May 18, 2021

Training data modification for training model

IBM0 citations63
US10990902B2Apr 27, 2021

Implementing a classification model for recognition processing

IBM0 citations63
US10991363B2Apr 27, 2021

Priors adaptation for conservative training of acoustic model

IBM0 citations63
US10923110B2Feb 16, 2021

Priors adaptation for conservative training of acoustic model

IBM0 citations63
US10909316B2Feb 2, 2021

Technique for automatically splitting words

IBM0 citations63
US10546230B2Jan 28, 2020

Generating labeled data by sequence-to-sequence modeling with added perturbations to encoded information

IBM1 citations63
US12288551B2Apr 29, 2025

Accuracy of streaming RNN transducer

IBM0 citations62
US12106215B2Oct 1, 2024

Knowledge transfer between recurrent neural networks

IBM0 citations62
US11908458B2Feb 20, 2024

Customization of recurrent neural network transducers for speech recognition

IBM1 citations62

KURATA GAKUTO

3 patents

NUANCE COMMUNICATIONS INC

2 patents

ITOH NOBUYASU

2 patents

ACTIVISION PUBLISHING INC

1 patent

Showing the top 50 of 96 patents by PatentIndex Score.