Masayuki Suzuki
Masayuki Suzuki
IBM Research
Verified email at - Homepage
Cited by
Cited by
Efficient Knowledge Distillation from an Ensemble of Teachers.
T Fukuda, M Suzuki, G Kurata, S Thomas, J Cui, B Ramabhadran
Interspeech, 3697-3701, 2017
Major depressive disorder discrimination using vocal acoustic features
T Taguchi, H Tachikawa, K Nemoto, M Suzuki, T Nagano, R Tachibana, ...
Journal of affective disorders 225, 214-220, 2018
Speech recognition model construction method, speech recognition method, computer system, speech recognition apparatus, program, and recording medium
G Kurata, T Nagano, M Suzuki, R Tachibana
US Patent 9,812,122, 2017
Pharmacological studies on medicinal plant components. I. On the extracts of Ophiopogon and some folk medicine
M Shibata, R Noguchi, M Suzuki, H Iwase, K Soeda, K Niwayama, ...
Proc Hoshi Pharm 13 (1), 66-76, 1971
Speech structure and its application to robust speech processing
N Minematsu, S Asakawa, M Suzuki, Y Qiao
New Generation Computing 28, 299-319, 2010
Automatic Chinese pronunciation error detection using SVM trained with structural features
T Zhao, A Hoshino, M Suzuki, N Minematsu, K Hirose
2012 IEEE Spoken Language Technology Workshop (SLT), 473-478, 2012
Low temperature specific heat, magnetic susceptibility and electrical resistivity measurements in Ni-Ti metallic glasses
S Kanemaki, M Suzuki, Y Yamada, U Mizutani
Journal of Physics F: Metal Physics 18 (1), 105, 1988
Improvements to n-gram language model using text generated from neural language model
M Suzuki, N Itoh, T Nagano, G Kurata, S Thomas
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
Accent sandhi estimation of Tokyo dialect of Japanese using conditional random fields
M Suzuki, R Kuroiwa, K Innami, S Kobayashi, S Shimizu, N Minematsu, ...
IEICE TRANSACTIONS on Information and Systems 100 (4), 655-661, 2017
English broadcast news speech recognition by humans and machines
S Thomas, M Suzuki, Y Huang, G Kurata, Z Tuske, G Saon, B Kingsbury, ...
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
New Advances in Speaker Diarization.
H Aronowitz, W Zhu, M Suzuki, G Kurata, R Hoory
Interspeech, 279-283, 2020
Sub-structure-based estimation of pronunciation proficiency and classification of learners
M Suzuki, N Minematsu, D Luo, K Hirose
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 574-579, 2009
Magnetoresistance in crystalline and amorphous Fe-Co-Ni based alloys
M Inagaki, M Suzuki, Y Iwama, U Mizutani
Japanese journal of applied physics 25 (10R), 1514, 1986
Effect and analysis of large-scale language model rescoring on competitive ASR systems
T Udagawa, M Suzuki, G Kurata, N Itoh, G Saon
arXiv preprint arXiv:2204.00212, 2022
Use of small unit language model for training large unit language models
M Suzuki, N Itoh, G Kurata
US Patent 10,832,657, 2020
Integration of multilayer regression analysis with structure-based pronunciation assessment
M Suzuki, Y Qiao, N Minematsu, K Hirose
Eleventh Annual Conference of the International Speech Communication Association, 2010
Affine invariant features and their application to speech recognition
Y Qiao, M Suzuki, N Minematsu
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings
M Suzuki, R Tachibana, S Thomas, B Ramabhadran, G Saon
Interspeech 2016, 1588-1592, 2016
Development of a web framework for teaching and learning Japanese prosody: OJAD (online Japanese accent dictionary).
I Nakamura, N Minematsu, M Suzuki, H Hirano, C Nakagawa, ...
INTERSPEECH, 2554-2558, 2013
Data augmentation based on vowel stretch for improving children's speech recognition
T Nagano, T Fukuda, M Suzuki, G Kurata
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
The system can't perform the operation now. Try again later.
Articles 1–20