Takashi Fukuda

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Improving ASR Robustness in Noisy Condition Through VAD Integration.

[BibT_eX]

[DOI]

Sashi Novitasari

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

Global RNN Transducer Models For Multi-dialect Speech Recognition.

[BibT_eX]

[DOI]

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.

[BibT_eX]

[DOI]

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.

[BibT_eX]

[DOI]

Tohru Nagano

CoRR, 2021

Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer.

[BibT_eX]

[DOI]

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.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Implicit Transfer of Privileged Acoustic Information in a Generalized Knowledge Distillation Framework.

[BibT_eX]

[DOI]

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

2019

Direct Neuron-Wise Fusion of Cognate Neural Networks.

[BibT_eX]

[DOI]

Masayuki Suzuki

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

Automated Testing of Basic Recognition Capability for Speech Recognition Systems.

[BibT_eX]

[DOI]

Futoshi Iwama

Proceedings of the 12th IEEE Conference on Software Testing, Validation and Verification, 2019

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

[BibT_eX]

[DOI]

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

Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation.

[BibT_eX]

[DOI]

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

2018

Detecting breathing sounds in realistic Japanese telephone conversations and its application to automatic speech recognition.

[BibT_eX]

[DOI]

Speech Commun., 2018

Data Augmentation Improves Recognition of Foreign Accented Speech.

[BibT_eX]

[DOI]

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

2017

Factorial Modeling for Effective Suppression of Directional Noise.

[BibT_eX]

[DOI]

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

Ensembles of Multi-Scale VGG Acoustic Models.

[BibT_eX]

[DOI]

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

Efficient Knowledge Distillation from an Ensemble of Teachers.

[BibT_eX]

[DOI]

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

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

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

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

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

An Inductive Method to Select Simulation Points.

[BibT_eX]

[DOI]

IEICE Trans. Inf. Syst., 2016

Convolutional neural network pre-trained with projection matrices on linear discriminant analysis.

[BibT_eX]

[DOI]

Ryuki Tachibana

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2014

Class number calculation using Siegel functions.

[BibT_eX]

[DOI]

LMS J. Comput. Math., 2014

Regularized feature-space discriminative adaptation for robust ASR.

[BibT_eX]

[DOI]

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

2013

Channel-mapping for speech corpus recycling.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Model-based noise reduction leveraging frequency-wise confidence metric for in-car speech recognition.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Constructing ensembles of dissimilar acoustic models using hidden attributes of training data.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Breath-Detection-Based Telephony Speech Phrasing.

[BibT_eX]

[DOI]

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

Combining Feature Space Discriminative Training with Long-Term Spectro-Temporal Features for Noise-Robust Speech Recognition.

[BibT_eX]

[DOI]

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

Retweet Reputation: A Bias-Free Evaluation Method for Tweeted Contents.

[BibT_eX]

[DOI]

Proceedings of the Social Innovation and Social Media, 2011

Frame-level AnyBoost for LVCSR with the MMI Criterion.

[BibT_eX]

[DOI]

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Dynamic Features in the Linear-Logarithmic Hybrid Domain for Automatic Speech Recognition in a Reverberant Environment.

[BibT_eX]

[DOI]

IEEE J. Sel. Top. Signal Process., 2010

Long-Term Spectro-Temporal and Static Harmonic Features for Voice Activity Detection.

[BibT_eX]

[DOI]

IEEE J. Sel. Top. Signal Process., 2010

DOA Estimation with Local-Peak-Weighted CSP.

[BibT_eX]

[DOI]

EURASIP J. Adv. Signal Process., 2010

Improved voice activity detection using static harmonic features.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

On the Iwasawa λ-invariant of the cyclotomic ℤ2-extension of ℚ(√p).

[BibT_eX]

[DOI]

Math. Comput., 2009

Weber's Class Number Problem in the Cyclotomic ℤ2-Extension of ℚ.

[BibT_eX]

[DOI]

Exp. Math., 2009

Dynamic features in the linear domain for robust automatic speech recognition in a reverberant environment.

[BibT_eX]

[DOI]

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

2008

Local Peak Enhancement for In-Car Speech Recognition in Noisy Environment.

[BibT_eX]

[DOI]

IEICE Trans. Inf. Syst., 2008

Canonicalization of Feature Parameters for Robust Speech Recognition Based on Distinctive Phonetic Feature (DPF) Vectors.

[BibT_eX]

[DOI]

IEICE Trans. Inf. Syst., 2008

Eigenpolarization States of Photoinduced Anisotropy in Azobenzene Film.

[BibT_eX]

[DOI]

IEICE Trans. Electron., 2008

Short- and long-term dynamic features for robust speech recognition.

[BibT_eX]

[DOI]

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Phone-duration-dependent long-term dynamic features for a stochastic model-based voice activity detection.

[BibT_eX]

[DOI]

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Local peak enhancement combined with noise reduction algorithms for robust automatic speech recognition in automobiles.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2008

2006

PS-ZCPA Based Feature Extraction with Auditory Masking, Modulation Enhancement and Noise Reduction for Robust ASR.

[BibT_eX]

[DOI]

IEICE Trans. Inf. Syst., 2006

An Algorithm for Computing p-Class Groups of Abelian Number Fields.

[BibT_eX]

[DOI]

Miho Aoki

Proceedings of the Algorithmic Number Theory, 7th International Symposium, 2006

2005

Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique.

[BibT_eX]

[DOI]

Muhammad Ghulam

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

Pitch-Synchronous ZCPA (PS-ZCPA)-Based Feature Extraction with Auditory Masking.

[BibT_eX]

[DOI]

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Orthogonalized Distinctive Phonetic Feature Extraction for Noise-Robust Automatic Speech Recognition.

[BibT_eX]

[DOI]

IEICE Trans. Inf. Syst., 2004

A noise-robust feature extraction method based on pitch-synchronous ZCPA for ASR.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Canonicalization of feature parameters for automatic speech recognition.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

2003

Voice quality normalization in an utterance for robust ASR.

[BibT_eX]

[DOI]

Muhammad Ghulam

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Noise-robust automatic speech recognition using orthogonalized distinctive phonetic feature vectors.

[BibT_eX]

[DOI]

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Noise-robust ASR by using distinctive phonetic features approximated with logarithmic normal distribution of HMM.

[BibT_eX]

[DOI]

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Distinctive phonetic feature extraction for robust speech recognition.

[BibT_eX]

[DOI]

Wataru Yamamoto

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Noncyclotomic Z p -Extensions of Imaginary Quadratic Fields.

[BibT_eX]

[DOI]

Exp. Math., 2002

Improving performance of an HMM-based ASR system by using monophone-level normalized confidence measure.

[BibT_eX]

[DOI]

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

Confidence scoring for accurate HMM-based word recognition by using SM-based monophone score normalization.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2002

An Application of Siegel Modular Functions to Kronecker's Limit Formula.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Number Theory, 5th International Symposium, 2002

2001

On Iwasawa lambda3-invariants of cyclic cubic fields of prime conductor.

[BibT_eX]

[DOI]

Math. Comput., 2001

Peripheral features for HMM-based speech recognition.

[BibT_eX]

[DOI]

Masashi Takigawa

Proceedings of the IEEE International Conference on Acoustics, 2001

2000

On a unit group generated by special values of Siegel modular functions.

[BibT_eX]

[DOI]

Math. Comput., 2000

A novel feature extraction using multiple acoustic feature planes for HMM-based speech recognition.

[BibT_eX]

[DOI]

Masashi Takigawa

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

1996

A capitulation problem and Greenberg's conjecture on real quadratic fields.

[BibT_eX]

[DOI]

Math. Comput., 1996

Cyclotomic units and Greenberg's conjecture for real quadratic fields.

[BibT_eX]

[DOI]