Gakuto Kurata

According to our database, Gakuto Kurata authored at least 61 papers between 2002 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems.

Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon

Proceedings of the IEEE International Conference on Acoustics, 2024

Robust ASR Error Correction with Conservative Data Filtering.

Takuma Udagawa, Masayuki Suzuki, Masayasu Muraoka, Gakuto Kurata

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

2023

Speech-enriched Memory for Inference-time Adaptation of ASR Models to Word Dictionaries.

Ashish R. Mittal, Sunita Sarawagi, Preethi Jyothi, George Saon, Gakuto Kurata

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems.

Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Improving ASR Robustness in Noisy Condition Through VAD Integration.

Sashi Novitasari, Takashi Fukuda, Gakuto Kurata

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Global RNN Transducer Models For Multi-dialect Speech Recognition.

Takashi Fukuda, Samuel Thomas, Masayuki Suzuki, Gakuto Kurata, George Saon, Brian Kingsbury

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing.

Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

Knowledge Distillation Leveraging Alternative Soft Targets from Non-Parallel Qualified Speech Data.

Tohru Nagano, Takashi Fukuda, Gakuto Kurata

CoRR, 2021

Improving Customization of Neural Transducers by Mitigating Acoustic Mismatch of Synthesized Audio.

Gakuto Kurata, George Saon, Brian Kingsbury, David Haws, Zoltán Tüske

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering.

Takashi Fukuda, Gakuto Kurata

Proceedings of the IEEE International Conference on Acoustics, 2021

RNN Transducer Models for Spoken Language Understanding.

Samuel Thomas, Hong-Kwang Jeff Kuo, George Saon, Zoltán Tüske, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Knowledge Distillation from Offline to Streaming RNN Transducer for End-to-End Speech Recognition.

Gakuto Kurata, George Saon

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

End-to-End Spoken Language Understanding Without Full Transcripts.

Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis A. Lastras

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

New Advances in Speaker Diarization.

Hagai Aronowitz, Weizhong Zhu, Masayuki Suzuki, Gakuto Kurata, Ron Hoory

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Speaker Embeddings Incorporating Acoustic Conditions for Diarization.

Yosuke Higuchi, Masayuki Suzuki, Gakuto Kurata

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Converting Written Language to Spoken Language with Neural Machine Translation for Language Modeling.

Shintaro Ando, Masayuki Suzuki, Nobuyasu Itoh, Gakuto Kurata, Nobuaki Minematsu

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Multi-Task CTC Training with Auxiliary Feature Reconstruction for End-to-End Speech Recognition.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Direct Neuron-Wise Fusion of Cognate Neural Networks.

Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

English Broadcast News Speech Recognition by Humans and Machines.

Samuel Thomas, Masayuki Suzuki, Yinghui Huang, Gakuto Kurata, Zoltán Tüske, George Saon, Brian Kingsbury, Michael Picheny, Tom Dibert, Alice Kaiser-Schatzlein, Bern Samko

Proceedings of the IEEE International Conference on Acoustics, 2019

Improvements to N-gram Language Model Using Text Generated from Neural Language Model.

Masayuki Suzuki, Nobuyasu Itoh, Tohru Nagano, Gakuto Kurata, Samuel Thomas

Proceedings of the IEEE International Conference on Acoustics, 2019

Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition.

Tohru Nagano, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models.

Masayuki Suzuki, Tohru Nagano, Gakuto Kurata, Samuel Thomas

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Data Augmentation Improves Recognition of Foreign Accented Speech.

Takashi Fukuda, Raul Fernandez, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Alexander Sorin, Gakuto Kurata

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Symbol Sequence Search from Telephone Conversation.

Masayuki Suzuki, Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, Kenneth Ward Church, Mark Drake

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

English Conversational Telephone Speech Recognition by Humans and Machines.

George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Empirical Exploration of Novel Architectures and Objectives for Language Models.

Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, George Saon

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Factorial Modeling for Effective Suppression of Directional Noise.

Osamu Ichikawa, Takashi Fukuda, Gakuto Kurata, Steven J. Rennie

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Ensembles of Multi-Scale VGG Acoustic Models.

Michael Heck, Masayuki Suzuki, Takashi Fukuda, Gakuto Kurata, Satoshi Nakamura

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Efficient Knowledge Distillation from an Ensemble of Teachers.

Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Samuel Thomas, Jia Cui, Bhuvana Ramabhadran

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Harmonic feature fusion for robust neural network-based acoustic modeling.

Osamu Ichikawa, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Bhuvana Ramabhadran

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Effective joint training of denoising feature space transforms and Neural Network based acoustic models.

Takashi Fukuda, Osamu Ichikawa, Gakuto Kurata, Ryuki Tachibana, Samuel Thomas, Bhuvana Ramabhadran

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Language modeling with highway LSTM.

Gakuto Kurata, Bhuvana Ramabhadran, George Saon, Abhinav Sethy

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016

Leveraging Sentence-level Information with Encoder LSTM for Natural Language Understanding.

Gakuto Kurata, Bing Xiang, Bowen Zhou, Mo Yu

CoRR, 2016

Improved Neural Network-based Multi-label Classification with Better Initialization Leveraging Label Co-occurrence.

Gakuto Kurata, Bing Xiang, Bowen Zhou

Proceedings of the NAACL HLT 2016, 2016

Labeled Data Generation with Encoder-Decoder LSTM for Semantic Slot Filling.

Gakuto Kurata, Bing Xiang, Bowen Zhou

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Improved Neural Network Initialization by Grouping Context-Dependent Targets for Acoustic Modeling.

Gakuto Kurata, Brian Kingsbury

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Speech recognition robust against speech overlapping in monaural recordings of telephone conversations.

Masayuki Suzuki, Gakuto Kurata, Tohru Nagano, Ryuki Tachibana

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling.

Gakuto Kurata, Bing Xiang, Bowen Zhou, Mo Yu

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016

2015

Discriminative re-ranking for automatic speech recognition by leveraging invariant structures.

Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu

Speech Commun., 2015

Deep neural network training emphasizing central frames.

Gakuto Kurata, Daniel Willett

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

A metric for evaluating speech recognizer output based on human-perception model.

Nobuyasu Itoh, Gakuto Kurata, Ryuki Tachibana, Masafumi Nishimura

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

2014

Leveraging phonetic context dependent invariant structure for continuous speech recognition.

Congying Zhang, Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu

Proceedings of the IEEE China Summit & International Conference on Signal and Information Processing, 2014

2012

Acoustically discriminative language model training with pseudo-hypothesis.

Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, Ariya Rastrow, Nobuyasu Itoh, Masafumi Nishimura

Speech Commun., 2012

Leveraging word confusion networks for named entity modeling and detection from conversational telephone speech.

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran

Speech Commun., 2012

Discriminative Reranking for LVCSR Leveraging Invariant Structure.

Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2011

Continuous Digits Recognition Leveraging Invariant Structure.

Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Acoustic Model Training with Detecting Transcription Errors in the Training Data.

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Named entity recognition from Conversational Telephone Speech leveraging Word Confusion Networks for training and recognition.

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran

Proceedings of the IEEE International Conference on Acoustics, 2011

Training of error-corrective model for ASR without using audio data.

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura

Proceedings of the IEEE International Conference on Acoustics, 2011

2009

Acoustically discriminative training for language models.

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura

Proceedings of the IEEE International Conference on Acoustics, 2009

2007

Automatic Prosody Labeling Using Multiple Models for Japanese.

Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, Noboru Babaguchi

IEICE Trans. Inf. Syst., 2007

Preliminary experiments toward automatic generation of new TTS voices from recorded speech alone.

Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, Noboru Babaguchi

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Unsupervised Lexicon Acquisition from Speech and Text.

Gakuto Kurata, Shinsuke Mori, Nobuyasu Itoh, Masafumi Nishimura

Proceedings of the IEEE International Conference on Acoustics, 2007

2006

Unsupervised Adaptation of a Stochastic Language Model Using a Japanese Raw Corpus.

Gakuto Kurata, Shinsuke Mori, Masafumi Nishimura

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Phoneme-to-Text Transcription System with an Infinite Vocabulary.

Shinsuke Mori, Daisuke Takuma, Gakuto Kurata

Proceedings of the ACL 2006, 2006

2005

Class-based variable memory length Markov model.

Shinsuke Mori, Gakuto Kurata

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

2004

GDQA: Graph Driven Question Answering System - NTCIR-4 QAC2 Experiments.

Gakuto Kurata, Naoaki Okazaki, Mitsuru Ishizuka

Proceedings of the Fourth NTCIR Workshop on Research in Information Access Technologies Information Retrieval, 2004

2002

Corpus-based analysis of English spoken by Japanese students in view of the entire phonemic system of English.

Nobuaki Minematsu, Gakuto Kurata, Keikichi Hirose

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Integration of MLLR adaptation with pronunciation proficiency adaptation for non-native speech recognition.

Nobuaki Minematsu, Gakuto Kurata, Keikichi Hirose

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002