Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition
Kurata, Gakuto, Audhkhasi, Kartik
Published in 2018 IEEE Spoken Language Technology Workshop (SLT) (01.12.2018)
Published in 2018 IEEE Spoken Language Technology Workshop (SLT) (01.12.2018)
Get full text
Conference Proceeding
Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering
Fukuda, Takashi, Kurata, Gakuto
Published in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (06.06.2021)
Published in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (06.06.2021)
Get full text
Conference Proceeding
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
Udagawa, Takuma, Suzuki, Masayuki, Kurata, Gakuto, Muraoka, Masayasu, Saon, George
Published in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (14.04.2024)
Published in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (14.04.2024)
Get full text
Conference Proceeding
Improvements to N-gram Language Model Using Text Generated from Neural Language Model
Suzuki, Masayuki, Itoh, Nobuyasu, Nagano, Tohru, Kurata, Gakuto, Thomas, Samuel
Published in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2019)
Published in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2019)
Get full text
Conference Proceeding
Converting Written Language to Spoken Language with Neural Machine Translation for Language Modeling
Ando, Shintaro, Suzuki, Masayuki, Itoh, Nobuyasu, Kurata, Gakuto, Minematsu, Nobuaki
Published in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2020)
Published in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2020)
Get full text
Conference Proceeding
RNN Transducer Models for Spoken Language Understanding
Thomas, Samuel, Kuo, Hong-Kwang J., Saon, George, Tuske, Zoltan, Kingsbury, Brian, Kurata, Gakuto, Kons, Zvi, Hoory, Ron
Published in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (06.06.2021)
Published in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (06.06.2021)
Get full text
Conference Proceeding
Harmonic feature fusion for robust neural network-based acoustic modeling
Ichikawa, Osamu, Fukuda, Takashi, Suzuki, Masayuki, Kurata, Gakuto, Ramabhadran, Bhuvana
Published in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2017)
Published in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2017)
Get full text
Conference Proceeding
English Broadcast News Speech Recognition by Humans and Machines
Thomas, Samuel, Suzuki, Masayuki, Huang, Yinghui, Kurata, Gakuto, Tuske, Zoltan, Saon, George, Kingsbury, Brian, Picheny, Michael, Dibert, Tom, Kaiser-Schatzlein, Alice, Samko, Bern
Published in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2019)
Published in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2019)
Get full text
Conference Proceeding
Speech recognition robust against speech overlapping in monaural recordings of telephone conversations
Suzuki, Masayuki, Kurata, Gakuto, Nagano, Tohru, Tachibana, Ryuki
Published in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2016)
Published in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2016)
Get full text
Conference Proceeding
Journal Article
Effective joint training of denoising feature space transforms and Neural Network based acoustic models
Fukuda, Takashi, Ichikawa, Osamu, Kurata, Gakuto, Tachibana, Ryuki, Thomas, Samuel, Ramabhadran, Bhuvana
Published in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2017)
Published in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.03.2017)
Get full text
Conference Proceeding
Training of error-corrective model for ASR without using audio data
Kurata, Gakuto, Itoh, Nobuyasu, Nishimura, Masafumi
Published in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2011)
Published in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2011)
Get full text
Conference Proceeding
Language modeling with highway LSTM
Kurata, Gakuto, Ramabhadran, Bhuvana, Saon, George, Sethy, Abhinav
Published in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (01.12.2017)
Published in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (01.12.2017)
Get full text
Conference Proceeding
Named entity recognition from Conversational Telephone Speech leveraging Word Confusion Networks for training and recognition
Kurata, Gakuto, Itoh, Nobuyasu, Nishimura, Masafumi, Sethy, Abhinav, Ramabhadran, Bhuvana
Published in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2011)
Published in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01.05.2011)
Get full text
Conference Proceeding
Acoustically discriminative training for language models
Kurata, G., Itoh, N., Nishimura, M.
Published in 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (01.04.2009)
Published in 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (01.04.2009)
Get full text
Conference Proceeding
Unsupervised Lexicon Acquisition from Speech and Text
Kurata, G., Mori, S., Itoh, N., Nishimura, M.
Published in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 (01.04.2007)
Published in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 (01.04.2007)
Get full text
Conference Proceeding
Leveraging phonetic context dependent invariant structure for continuous speech recognition
Congying Zhang, Suzuki, Masayuki, Kurata, Gakuto, Nishimura, Masafumi, Minematsu, Nobuaki
Published in 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) (01.07.2014)
Published in 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) (01.07.2014)
Get full text
Conference Proceeding