| 2025 | ASRU | Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities. | 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 | ICASSP | Knowledge Distillation Based Training of Unified Conformer CTC Models for Multi-form ASR. | Takashi Fukuda, Gakuto Kurata, George Saon |
| 2025 | Interspeech | Improving End-to-end Mixed-case ASR with Knowledge Distillation and Integration of Voice Activity Cues. | Sashi Novitasari, Takashi Fukuda, Gakuto Kurata |
| 2025 | Interspeech | Voice Activity-based Text Segmentation for ASR Text Denormalization. | Sashi Novitasari, Takashi Fukuda, Gakuto Kurata |
| 2023 | ICASSP | Effective Training of RNN Transducer Models on Diverse Sources of Speech and Text Data. | Takashi Fukuda, Samuel Thomas |
| 2022 | Interspeech | 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 |
| 2022 | Interspeech | Global RNN Transducer Models For Multi-dialect Speech Recognition. | Takashi Fukuda, Samuel Thomas, Masayuki Suzuki, Gakuto Kurata, George Saon, Brian Kingsbury |
| 2022 | Interspeech | Improving ASR Robustness in Noisy Condition Through VAD Integration. | Sashi Novitasari, Takashi Fukuda, Gakuto Kurata |
| 2021 | ICASSP | Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering. | Takashi Fukuda, Gakuto Kurata |
| 2021 | Interspeech | Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer. | Takashi Fukuda, Samuel Thomas |
| 2020 | Interspeech | Implicit Transfer of Privileged Acoustic Information in a Generalized Knowledge Distillation Framework. | Takashi Fukuda, Samuel Thomas |
| 2019 | ASRU | Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation. | Takashi Fukuda, Samuel Thomas |
| 2019 | ASRU | Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition. | Tohru Nagano, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata |
| 2019 | Interspeech | Direct Neuron-Wise Fusion of Cognate Neural Networks. | Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata |
| 2019 | ICST | Automated Testing of Basic Recognition Capability for Speech Recognition Systems. | Futoshi Iwama, Takashi Fukuda |
| 2018 | Interspeech | Data Augmentation Improves Recognition of Foreign Accented Speech. | Takashi Fukuda, Raul Fernandez, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Alexander Sorin, Gakuto Kurata |
| 2017 | ICASSP | 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 |
| 2017 | ICASSP | Harmonic feature fusion for robust neural network-based acoustic modeling. | Osamu Ichikawa, Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Bhuvana Ramabhadran |
| 2017 | Interspeech | Efficient Knowledge Distillation from an Ensemble of Teachers. | Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Samuel Thomas, Jia Cui, Bhuvana Ramabhadran |
| 2017 | Interspeech | Ensembles of Multi-Scale VGG Acoustic Models. | Michael Heck, Masayuki Suzuki, Takashi Fukuda, Gakuto Kurata, Satoshi Nakamura |
| 2017 | Interspeech | Factorial Modeling for Effective Suppression of Directional Noise. | Osamu Ichikawa, Takashi Fukuda, Gakuto Kurata, Steven J. Rennie |
| 2016 | ICASSP | Convolutional neural network pre-trained with projection matrices on linear discriminant analysis. | Takashi Fukuda, Osamu Ichikawa, Ryuki Tachibana |
| 2014 | Interspeech | Regularized feature-space discriminative adaptation for robust ASR. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura, Steven J. Rennie, Vaibhava Goel |
| 2013 | ICASSP | Channel-mapping for speech corpus recycling. | Osamu Ichikawa, Steven J. Rennie, Takashi Fukuda, Masafumi Nishimura |
| 2012 | ICASSP | Constructing ensembles of dissimilar acoustic models using hidden attributes of training data. | Takashi Fukuda, Ryuki Tachibana, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan |
| 2012 | ICASSP | Model-based noise reduction leveraging frequency-wise confidence metric for in-car speech recognition. | Osamu Ichikawa, Steven J. Rennie, Takashi Fukuda, Masafumi Nishimura |
| 2011 | ASRU | Frame-level AnyBoost for LVCSR with the MMI Criterion. | Ryuki Tachibana, Takashi Fukuda, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan |
| 2011 | Interspeech | Combining Feature Space Discriminative Training with Long-Term Spectro-Temporal Features for Noise-Robust Speech Recognition. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura |
| 2011 | Interspeech | Breath-Detection-Based Telephony Speech Phrasing. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura |
| 2011 | ICWSM | Retweet Reputation: A Bias-Free Evaluation Method for Tweeted Contents. | Shino Fujiki, Hiroya Yano, Takashi Fukuda, Hayato Yamana |
| 2010 | ICASSP | Improved voice activity detection using static harmonic features. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura |
| 2009 | Interspeech | Dynamic features in the linear domain for robust automatic speech recognition in a reverberant environment. | Osamu Ichikawa, Takashi Fukuda, Ryuki Tachibana, Masafumi Nishimura |
| 2008 | ICASSP | Local peak enhancement combined with noise reduction algorithms for robust automatic speech recognition in automobiles. | Osamu Ichikawa, Takashi Fukuda, Masafumi Nishimura |
| 2008 | Interspeech | Phone-duration-dependent long-term dynamic features for a stochastic model-based voice activity detection. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura |
| 2008 | Interspeech | Short- and long-term dynamic features for robust speech recognition. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura |
| 2005 | ICASSP | Pitch-Synchronous ZCPA (PS-ZCPA)-Based Feature Extraction with Auditory Masking. | Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, Tsuneo Nitta |
| 2005 | Interspeech | Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique. | Takashi Fukuda, Muhammad Ghulam, Tsuneo Nitta |
| 2004 | Interspeech | Canonicalization of feature parameters for automatic speech recognition. | Takashi Fukuda, Tsuneo Nitta |
| 2004 | Interspeech | A noise-robust feature extraction method based on pitch-synchronous ZCPA for ASR. | Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, Tsuneo Nitta |
| 2003 | ICASSP | Distinctive phonetic feature extraction for robust speech recognition. | Takashi Fukuda, Wataru Yamamoto, Tsuneo Nitta |
| 2003 | Interspeech | Noise-robust ASR by using distinctive phonetic features approximated with logarithmic normal distribution of HMM. | Takashi Fukuda, Tsuneo Nitta |
| 2003 | Interspeech | Noise-robust automatic speech recognition using orthogonalized distinctive phonetic feature vectors. | Takashi Fukuda, Tsuneo Nitta |
| 2003 | Interspeech | Voice quality normalization in an utterance for robust ASR. | Muhammad Ghulam, Takashi Fukuda, Tsuneo Nitta |
| 2002 | ICASSP | Confidence scoring for accurate HMM-based word recognition by using SM-based monophone score normalization. | Takaharu Sato, Muhammad Ghulam, Takashi Fukuda, Tsuneo Nitta |
| 2002 | Interspeech | Improving performance of an HMM-based ASR system by using monophone-level normalized confidence measure. | Muhammad Ghulam, Takashi Fukuda, Takaharu Sato, Tsuneo Nitta |
| 2001 | ICASSP | Peripheral features for HMM-based speech recognition. | Takashi Fukuda, Masashi Takigawa, Tsuneo Nitta |
| 2000 | Interspeech | A novel feature extraction using multiple acoustic feature planes for HMM-based speech recognition. | Tsuneo Nitta, Masashi Takigawa, Takashi Fukuda |