Yuuki Tachioka

52 papers A 5C 1Misc 5Journal 3Unranked 37

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Automated Pronunciation Scoring of Child L2 Learners with Score Calibration for Imbalanced Distributions. MLSP Yuuki Tachioka
2025	—	`conf`	Cell Entity Annotation for SemTab 2025 MammoTab via Iterative Refinement with Transposed Contexts and Unsupervised Scoring. OM@ISWC Yuuki Tachioka, Yasunori Terao
2025	—	`conf`	Contrastive Learning of Temporal and Event-Based Behavioral Views for Universal User Embeddings. APSIPA Yuuki Tachioka
2025	—	`conf`	Decoder-free Audio Watermarking via Visual Cryptography in Time-Frequency Domain. CANDARW Yuuki Tachioka
2025	—	`conf`	Enhancing Pathloss Estimation with Vision Transformers and Direct Wave Power Integration. EUSIPCO Yuuki Tachioka
2025	—	`conf`	Fusion-in-LLM: A Parallel Approach to Improve Retrieval-Augmented Generation for Quiz-Based Question Answering. NLDB (2) Yuuki Tachioka
2025	—	`conf`	KP4POI: Efficient POI Recommendation on Large-scale Datasets via Knowledge Prompting of Venues and Users. RecTour@RecSys Yuuki Tachioka
2025	—	`conf`	Overview of the NTCIR-18 Transfer-2 Task. NTCIR Hideo Joho, Atsushi Keyaki, Yuuki Tachioka, Shuhei Yamamoto
2025	—	`conf`	ditlab at the NTCIR-18 Transfer-2 Task. NTCIR Yuuki Tachioka, Yasunori Terao
2024	—	`conf`	Blind Anomalous Sound Detection without Specifying Target Type. GCCE Yuuki Tachioka
2024	—	`conf`	Building Test Collections for Japanese Dense Information Retrieval Technologies and Beyond. EMTCIR/UM-CIR@SIGIR-AP Hideo Joho, Atsushi Keyaki, Yuuki Tachioka, Shuhei Yamamoto
2024	—	`conf`	Outlier Exposure with Efficient Division of Positive and Negative Examples for Anomalous Sound Detection. EUSIPCO Yuuki Tachioka
2024	—	`conf`	Question Answer Summary Generation from Unstructured Texts by Using LLMs. DASFAA (Workshops) Yuuki Tachioka
2024	—	`conf`	Restoration of hyperspectral images from RGB images by using two-band models. ICCCM Yuuki Tachioka
2024	A	`conf`	User Knowledge Prompt for Sequential Recommendation. RecSys Yuuki Tachioka
2023	—	`conf`	Analysis of Embedding Space of Speech Synthesis System as High-Dimension, Low-Sample-Size Data. GCCE Yuuki Tachioka
2023	—	`conf`	ditlab at the NTCIR-17 QA Lab-PoliInfo-4 Task. NTCIR Yuuki Tachioka
2023	—	`conf`	ditlab at the NTCIR-17 Transfer Task. NTCIR Yuuki Tachioka
2022	—	`conf`	Multi-condition Training and System Combination for Automatic MOS Prediction. GCCE Yuuki Tachioka
2022	—	`conf`	Privacy preservation satisfying utility requirements based on multi-objective optimization. SCIS/ISIS Yuuki Tachioka
2022	—	`conf`	ditlab at the NTCIR-16 QA Lab-PoliInfo-3. NTCIR Yuuki Tachioka, Atsushi Keyaki
2022	J	`jnl`	ditlab system for Dialogue Robot Competition 2022. CoRR Yuuki Tachioka
2021	—	`conf`	Exponentiated Geometric-Mean-Balanced Mask for Underdetermined Source Separation. GCCE Yuuki Tachioka
2021	—	`conf`	Integration of Annotator-wise Estimations for Emotion Recognition by Using Group Softmax. APSIPA ASC Yuuki Tachioka
2020	—	`conf`	Multilingual acoustic model training based on phoneme set conversion. GCCE Yuuki Tachioka
2020	—	`conf`	Privacy Preserving Acoustic Model Training for Speech Recognition. APSIPA Yuuki Tachioka
2020	—	`conf`	Sparse Independent Vector Analysis Based on Mel Filter. GCCE Takahiro Ushijima, Yuuki Tachioka, Shingo Uenohara, Ken'ichi Furuya
2019	—	`conf`	Activation Driven Synchronized Joint Diagonalization for Underdetermined Sound Source Separation. APSIPA Taiki Izumi, Shingo Uenohara, Ken'ichi Furuya, Yuuki Tachioka
2019	Misc	`conf`	Automatic Determination of the Optimum Number of Updates in Synchronized Joint Diagonalization. CISIS Taiki Izumi, Yuuki Tachioka, Shingo Uenohara, Ken'ichi Furuya
2019	—	`conf`	Hypothesis Correction Based on Semi-character Recurrent Neural Network for End-to-end Speech Recognition. APSIPA Yuuki Tachioka
2019	—	`conf`	Knowledge Distillation Using Soft and Hard Labels and Annealing for Acoustic Model Training. GCCE Yuuki Tachioka
2019	—	`conf`	Permutation Alignment Based on MUSIC Spectrum Discrepancy for Blind Source Separation. EUSIPCO Yuuki Tachioka
2018	Misc	`conf`	Dnn-Based Voice Activity Detection Using Auxiliary Speech Models in Noisy Environments. ICASSP Yuuki Tachioka
2018	—	`conf`	Multi-channel Non-negative Matrix Factorization Initialized with Full-rank and Rank-1 Spatial Correlation Matrix for Speech Recognition. ISPACS Yuuki Tachioka
2017	—	`ch.`	Advanced ASR Technologies for Mitsubishi Electric Speech Applications. New Era for Robust Speech Recognition, Exploiting Deep Learning Yuuki Tachioka, Toshiyuki Hanazawa, Tomohiro Narita, Jun Ishii
2017	A	`conf`	Coupled Initialization of Multi-Channel Non-Negative Matrix Factorization Based on Spatial and Spectral Information. INTERSPEECH Yuuki Tachioka, Tomohiro Narita, Iori Miura, Takanobu Uramoto, Natsuki Monta, Shingo Uenohara, Ken'ichi Furuya, Shinji Watanabe, Jonathan Le Roux
2017	J	`jnl`	Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones. J. Inf. Process. Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2017	—	`conf`	Sequential initialization of multichannel nonnegative matrix factorization for sound source separation. GCCE Takanobu Uramoto, Yuuki Tachioka, Tomohiro Narita, Iori Miura, Shingo Uenohara, Ken'ichi Furuya
2016	—	`conf`	Optimal automatic speech recognition system selection for noisy environments. APSIPA Yuuki Tachioka, Tomohiro Narita
2015	Misc	`conf`	Discriminative method for recurrent neural network language models. ICASSP Yuuki Tachioka, Shinji Watanabe
2015	J	`jnl`	Effectiveness of dereverberation, feature transformation, discriminative training methods, and system combination approach for various reverberant environments. EURASIP J. Adv. Signal Process. Yuuki Tachioka, Tomohiro Narita, Shinji Watanabe
2015	—	`conf`	Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN. APSIPA Hiroki Kanagawa, Yuuki Tachioka, Shinji Watanabe, Jun Ishii
2015	A	`conf`	Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features. INTERSPEECH Yuuki Tachioka, Shinji Watanabe
2014	Misc	`conf`	Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. ICASSP Felix Weninger, Shinji Watanabe, Yuuki Tachioka, Björn W. Schuller
2014	—	`conf`	Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments. HSCMA Yuuki Tachioka, Tomohiro Narita, Shinji Watanabe, Jonathan Le Roux
2014	—	`conf`	Sequence discriminative training for low-rank deep neural networks. GlobalSIP Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2014	A	`conf`	Sequential maximum mutual information linear discriminant analysis for speech recognition. INTERSPEECH Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2013	C	`conf`	A generalized discriminative training framework for system combination. ASRU Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2013	A	`conf`	Discriminative training of acoustic models for system combination. INTERSPEECH Yuuki Tachioka, Shinji Watanabe
2013	Misc	`conf`	Effectiveness of discriminative training and feature transformation for reverberated and noisy speech. ICASSP Yuuki Tachioka, Shinji Watanabe, John R. Hershey
2013	—	`conf`	Objective Measurement of the Relationship between Variants in Classical Literature. Culture and Computing Yuuki Tachioka
2013	—	`conf`	Voice activity detection based on density ratio estimation and system combination. APSIPA Yuuki Tachioka, Toshiyuki Hanazawa, Tomohiro Narita, Jun Ishii