Takashi Fukuda

72 papers A 27C 4Misc 13Journal 22Unranked 6

Year	Rank	Type	Title / Venue / Authors
2025	C	`conf`	Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities. ASRU George Saon, Avihu Dekel, Alexander Brooks, Tohru Nagano, Abraham Daniels, Aharon Satt, Ashish R. Mittal, Brian Kingsbury, David Haws, Edmilson Da Silva Morais, Gakuto Kurata, Hagai Aronowitz, Ibrahim Ibrahim, Hong-Kwang Kuo, Kate Soule, Luis A. Lastras, Masayuki Suzuki, Ron Hoory, Samuel Thomas, Sashi Novitasari, Takashi Fukuda, Vishal Sunder, Xiaodong Cui, Zvi Kons
2025	A	`conf`	Improving End-to-end Mixed-case ASR with Knowledge Distillation and Integration of Voice Activity Cues. INTERSPEECH Sashi Novitasari, Takashi Fukuda, Gakuto Kurata
2025	Misc	`conf`	Knowledge Distillation Based Training of Unified Conformer CTC Models for Multi-form ASR. ICASSP Takashi Fukuda, Gakuto Kurata, George Saon
2025	A	`conf`	Voice Activity-based Text Segmentation for ASR Text Denormalization. INTERSPEECH Sashi Novitasari, Takashi Fukuda, Gakuto Kurata
2024	J	`jnl`	Simple Binding and Dissociation of a Sialoglycoprotein Using Boronic Acid-Modified Functional Interfaces on Microparticles. Sensors Yukichi Horiguchi, Masato Yasuura, Hiroki Ashiba, Zheng Lin Tan, Takashi Fukuda
2023	Misc	`conf`	Effective Training of RNN Transducer Models on Diverse Sources of Speech and Text Data. ICASSP Takashi Fukuda, Samuel Thomas
2023	J	`jnl`	Improvement of Sensitivity and Speed of Virus Sensing Technologies Using nm- and μm-Scale Components. Sensors Masato Yasuura, Zheng Lin Tan, Yukichi Horiguchi, Hiroki Ashiba, Takashi Fukuda
2022	A	`conf`	Global RNN Transducer Models For Multi-dialect Speech Recognition. INTERSPEECH Takashi Fukuda, Samuel Thomas, Masayuki Suzuki, Gakuto Kurata, George Saon, Brian Kingsbury
2022	A	`conf`	Improving ASR Robustness in Noisy Condition Through VAD Integration. INTERSPEECH Sashi Novitasari, Takashi Fukuda, Gakuto Kurata
2022	A	`conf`	Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing. INTERSPEECH Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata
2022	J	`jnl`	Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing. CoRR Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata
2021	Misc	`conf`	Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering. ICASSP Takashi Fukuda, Gakuto Kurata
2021	A	`conf`	Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer. Interspeech Takashi Fukuda, Samuel Thomas
2021	J	`jnl`	Knowledge Distillation Leveraging Alternative Soft Targets from Non-Parallel Qualified Speech Data. CoRR Tohru Nagano, Takashi Fukuda, Gakuto Kurata
2020	A	`conf`	Implicit Transfer of Privileged Acoustic Information in a Generalized Knowledge Distillation Framework. INTERSPEECH Takashi Fukuda, Samuel Thomas
2019	A	`conf`	Automated Testing of Basic Recognition Capability for Speech Recognition Systems. ICST Futoshi Iwama, Takashi Fukuda
2019	C	`conf`	Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition. ASRU Tohru Nagano, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata
2019	A	`conf`	Direct Neuron-Wise Fusion of Cognate Neural Networks. INTERSPEECH Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata
2019	C	`conf`	Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation. ASRU Takashi Fukuda, Samuel Thomas
2018	A	`conf`	Data Augmentation Improves Recognition of Foreign Accented Speech. INTERSPEECH Takashi Fukuda, Raul Fernandez, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Alexander Sorin, Gakuto Kurata
2018	J	`jnl`	Detecting breathing sounds in realistic Japanese telephone conversations and its application to automatic speech recognition. Speech Commun. Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2017	Misc	`conf`	Effective joint training of denoising feature space transforms and Neural Network based acoustic models. ICASSP Takashi Fukuda, Osamu Ichikawa, Gakuto Kurata, Ryuki Tachibana, Samuel Thomas, Bhuvana Ramabhadran
2017	A	`conf`	Efficient Knowledge Distillation from an Ensemble of Teachers. INTERSPEECH Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Samuel Thomas, Jia Cui, Bhuvana Ramabhadran
2017	A	`conf`	Ensembles of Multi-Scale VGG Acoustic Models. INTERSPEECH Michael Heck, Masayuki Suzuki, Takashi Fukuda, Gakuto Kurata, Satoshi Nakamura
2017	A	`conf`	Factorial Modeling for Effective Suppression of Directional Noise. INTERSPEECH Osamu Ichikawa, Takashi Fukuda, Gakuto Kurata, Steven J. Rennie
2017	Misc	`conf`	Harmonic feature fusion for robust neural network-based acoustic modeling. ICASSP Osamu Ichikawa, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Bhuvana Ramabhadran
2016	J	`jnl`	An Inductive Method to Select Simulation Points. IEICE Trans. Inf. Syst. Minseong Choi, Takashi Fukuda, Masahiro Goshima, Shuichi Sakai
2016	Misc	`conf`	Convolutional neural network pre-trained with projection matrices on linear discriminant analysis. ICASSP Takashi Fukuda, Osamu Ichikawa, Ryuki Tachibana
2015	—	`conf`	An Inductive Method to Select Simulation Points. CANDAR Minseong Choi, Takashi Fukuda, Masahiro Goshima, Shuichi Sakai
2014	J	`jnl`	Class number calculation using Siegel functions. LMS J. Comput. Math. Takashi Fukuda, Keiichi Komatsu
2014	A	`conf`	Regularized feature-space discriminative adaptation for robust ASR. INTERSPEECH Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura, Steven J. Rennie, Vaibhava Goel
2013	Misc	`conf`	Channel-mapping for speech corpus recycling. ICASSP Osamu Ichikawa, Steven J. Rennie, Takashi Fukuda, Masafumi Nishimura
2012	Misc	`conf`	Constructing ensembles of dissimilar acoustic models using hidden attributes of training data. ICASSP Takashi Fukuda, Ryuki Tachibana, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan
2012	Misc	`conf`	Model-based noise reduction leveraging frequency-wise confidence metric for in-car speech recognition. ICASSP Osamu Ichikawa, Steven J. Rennie, Takashi Fukuda, Masafumi Nishimura
2011	A	`conf`	Breath-Detection-Based Telephony Speech Phrasing. INTERSPEECH Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2011	A	`conf`	Combining Feature Space Discriminative Training with Long-Term Spectro-Temporal Features for Noise-Robust Speech Recognition. INTERSPEECH Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2011	C	`conf`	Frame-level AnyBoost for LVCSR with the MMI Criterion. ASRU Ryuki Tachibana, Takashi Fukuda, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan
2011	—	`conf`	Retweet Reputation: A Bias-Free Evaluation Method for Tweeted Contents. Social Innovation and Social Media Shino Fujiki, Hiroya Yano, Takashi Fukuda, Hayato Yamana
2010	J	`jnl`	DOA Estimation with Local-Peak-Weighted CSP. EURASIP J. Adv. Signal Process. Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura
2010	J	`jnl`	Dynamic Features in the Linear-Logarithmic Hybrid Domain for Automatic Speech Recognition in a Reverberant Environment. IEEE J. Sel. Top. Signal Process. Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura
2010	Misc	`conf`	Improved voice activity detection using static harmonic features. ICASSP Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2010	J	`jnl`	Long-Term Spectro-Temporal and Static Harmonic Features for Voice Activity Detection. IEEE J. Sel. Top. Signal Process. Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2009	A	`conf`	Dynamic features in the linear domain for robust automatic speech recognition in a reverberant environment. INTERSPEECH Osamu Ichikawa, Takashi Fukuda, Ryuki Tachibana, Masafumi Nishimura
2009	J	`jnl`	On the Iwasawa λ-invariant of the cyclotomic ℤ Math. Comput. Takashi Fukuda, Keiichi Komatsu
2009	J	`jnl`	Weber's Class Number Problem in the Cyclotomic ℤ Exp. Math. Takashi Fukuda, Keiichi Komatsu
2008	J	`jnl`	Canonicalization of Feature Parameters for Robust Speech Recognition Based on Distinctive Phonetic Feature (DPF) Vectors. IEICE Trans. Inf. Syst. Mohammad Nurul Huda, Muhammad Ghulam, Takashi Fukuda, Kouichi Katsurada, Tsuneo Nitta
2008	J	`jnl`	Eigenpolarization States of Photoinduced Anisotropy in Azobenzene Film. IEICE Trans. Electron. Daisuke Barada, Kiyonobu Tamura, Takashi Fukuda, Akira Emoto, Toyohiko Yatagai
2008	J	`jnl`	Local Peak Enhancement for In-Car Speech Recognition in Noisy Environment. IEICE Trans. Inf. Syst. Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura
2008	Misc	`conf`	Local peak enhancement combined with noise reduction algorithms for robust automatic speech recognition in automobiles. ICASSP Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura
2008	A	`conf`	Phone-duration-dependent long-term dynamic features for a stochastic model-based voice activity detection. INTERSPEECH Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2008	A	`conf`	Short- and long-term dynamic features for robust speech recognition. INTERSPEECH Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura
2006	—	`conf`	An Algorithm for Computing ANTS Miho Aoki, Takashi Fukuda
2006	J	`jnl`	PS-ZCPA Based Feature Extraction with Auditory Masking, Modulation Enhancement and Noise Reduction for Robust ASR. IEICE Trans. Inf. Syst. Muhammad Ghulam, Takashi Fukuda, Kouichi Katsurada, Junsei Horikawa, Tsuneo Nitta
2005	A	`conf`	Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique. INTERSPEECH Takashi Fukuda, Muhammad Ghulam, Tsuneo Nitta
2005	—	`conf`	Pitch-Synchronous ZCPA (PS-ZCPA)-Based Feature Extraction with Auditory Masking. ICASSP (1) Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, Tsuneo Nitta
2004	A	`conf`	A noise-robust feature extraction method based on pitch-synchronous ZCPA for ASR. INTERSPEECH Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, Tsuneo Nitta
2004	A	`conf`	Canonicalization of feature parameters for automatic speech recognition. INTERSPEECH Takashi Fukuda, Tsuneo Nitta
2004	J	`jnl`	Orthogonalized Distinctive Phonetic Feature Extraction for Noise-Robust Automatic Speech Recognition. IEICE Trans. Inf. Syst. Takashi Fukuda, Tsuneo Nitta
2003	—	`conf`	Distinctive phonetic feature extraction for robust speech recognition. ICASSP (2) Takashi Fukuda, Wataru Yamamoto, Tsuneo Nitta
2003	A	`conf`	Noise-robust ASR by using distinctive phonetic features approximated with logarithmic normal distribution of HMM. INTERSPEECH Takashi Fukuda, Tsuneo Nitta
2003	A	`conf`	Noise-robust automatic speech recognition using orthogonalized distinctive phonetic feature vectors. INTERSPEECH Takashi Fukuda, Tsuneo Nitta
2003	A	`conf`	Voice quality normalization in an utterance for robust ASR. INTERSPEECH Muhammad Ghulam, Takashi Fukuda, Tsuneo Nitta
2002	—	`conf`	An Application of Siegel Modular Functions to Kronecker's Limit Formula. ANTS Takashi Fukuda, Keiichi Komatsu
2002	Misc	`conf`	Confidence scoring for accurate HMM-based word recognition by using SM-based monophone score normalization. ICASSP Takaharu Sato, Muhammad Ghulam, Takashi Fukuda, Tsuneo Nitta
2002	A	`conf`	Improving performance of an HMM-based ASR system by using monophone-level normalized confidence measure. INTERSPEECH Muhammad Ghulam, Takashi Fukuda, Takaharu Sato, Tsuneo Nitta
2002	J	`jnl`	Noncyclotomic Z Exp. Math. Takashi Fukuda, Keiichi Komatsu
2001	J	`jnl`	On Iwasawa lambda Math. Comput. Takashi Fukuda, Keiichi Komatsu
2001	Misc	`conf`	Peripheral features for HMM-based speech recognition. ICASSP Takashi Fukuda, Masashi Takigawa, Tsuneo Nitta
2000	A	`conf`	A novel feature extraction using multiple acoustic feature planes for HMM-based speech recognition. INTERSPEECH Tsuneo Nitta, Masashi Takigawa, Takashi Fukuda
2000	J	`jnl`	On a unit group generated by special values of Siegel modular functions. Math. Comput. Takashi Fukuda, Keiichi Komatsu
1996	J	`jnl`	A capitulation problem and Greenberg's conjecture on real quadratic fields. Math. Comput. Takashi Fukuda, Keiichi Komatsu
1996	J	`jnl`	Cyclotomic units and Greenberg's conjecture for real quadratic fields. Math. Comput. Takashi Fukuda