Tatsuya Komatsu

90 papers A 11C 2Misc 22Journal 36Unranked 18

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	Aligned Contrastive Learning for Text-to-Music Retrieval. ICASSP Tatsuya Komatsu, Hokuto Munakata, Takuya Hasumi, Yusuke Fujita
2025	J	`jnl`	CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries. CoRR Hokuto Munakata, Takehiro Imamura, Taichi Nishimura, Tatsuya Komatsu
2025	Misc	`conf`	DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information. ICASSP Shota Nakada, Taichi Nishimura, Hokuto Munakata, Masayoshi Kondo, Tatsuya Komatsu
2025	J	`jnl`	Hallucination Localization in Video Captioning. CoRR Shota Nakada, Kazuhiro Saito, Yuchi Ishikawa, Hokuto Munakata, Tatsuya Komatsu, Masayoshi Kondo
2025	A	`conf`	Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos. INTERSPEECH Yuchi Ishikawa, Shota Nakada, Hokuto Munakata, Kazuhiro Saito, Tatsuya Komatsu, Yoshimitsu Aoki
2025	J	`jnl`	Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos. CoRR Yuchi Ishikawa, Shota Nakada, Hokuto Munakata, Kazuhiro Saito, Tatsuya Komatsu, Yoshimitsu Aoki
2025	Misc	`conf`	Language-based Audio Moment Retrieval. ICASSP Hokuto Munakata, Taichi Nishimura, Shota Nakada, Tatsuya Komatsu
2025	A	`conf`	Leveraging Unlabeled Audio for Audio-Text Contrastive Learning via Audio-Composed Text Features. INTERSPEECH Tatsuya Komatsu, Hokuto Munakata, Yuchi Ishikawa
2025	J	`jnl`	Listening without Looking: Modality Bias in Audio-Visual Captioning. CoRR Yuchi Ishikawa, Toranosuke Manabe, Tatsuya Komatsu, Yoshimitsu Aoki
2025	Misc	`conf`	Music Tagging with Classifier Group Chains. ICASSP Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita
2025	J	`jnl`	Music Tagging with Classifier Group Chains. CoRR Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita
2025	Misc	`conf`	Pre-training with Synthetic Patterns for Audio. ICASSP Yuchi Ishikawa, Tatsuya Komatsu, Yoshimitsu Aoki
2025	J	`jnl`	ProLAP: Probabilistic Language-Audio Pre-Training. CoRR Toranosuke Manabe, Yuchi Ishikawa, Hokuto Munakata, Tatsuya Komatsu
2025	J	`jnl`	Self-supervised learning method using multiple sampling strategies for general-purpose audio representation. CoRR Ibuki Kuroyanagi, Tatsuya Komatsu
2024	Misc	`conf`	Audio Difference Learning for Audio Captioning. ICASSP Tatsuya Komatsu, Yusuke Fujita, Kazuya Takeda, Tomoki Toda
2024	A	`conf`	Audio Fingerprinting with Holographic Reduced Representations. INTERSPEECH Yusuke Fujita, Tatsuya Komatsu
2024	J	`jnl`	Audio Fingerprinting with Holographic Reduced Representations. CoRR Yusuke Fujita, Tatsuya Komatsu
2024	J	`jnl`	DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information. CoRR Shota Nakada, Taichi Nishimura, Hokuto Munakata, Masayoshi Kondo, Tatsuya Komatsu
2024	Misc	`conf`	Keep Decoding Parallel With Effective Knowledge Distillation From Language Models To End-To-End Speech Recognisers. ICASSP Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita
2024	J	`jnl`	Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers. CoRR Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita
2024	J	`jnl`	Language-based Audio Moment Retrieval. CoRR Hokuto Munakata, Taichi Nishimura, Shota Nakada, Tatsuya Komatsu
2024	—	`conf`	Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection. EMNLP (System Demonstrations) Taichi Nishimura, Shota Nakada, Hokuto Munakata, Tatsuya Komatsu
2024	J	`jnl`	Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection. CoRR Taichi Nishimura, Shota Nakada, Hokuto Munakata, Tatsuya Komatsu
2024	J	`jnl`	Pre-training with Synthetic Patterns for Audio. CoRR Yuchi Ishikawa, Tatsuya Komatsu, Yoshimitsu Aoki
2024	Misc	`conf`	PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions. ICASSP Reo Shimizu, Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana
2024	A	`conf`	Universal Score-based Speech Enhancement with High Content Preservation. INTERSPEECH Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu
2024	J	`jnl`	Universal Score-based Speech Enhancement with High Content Preservation. CoRR Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu
2023	C	`conf`	Analysis of Biological Data of Cows and Development of Detection Systems for Calving Phase. IECON Hiroto Noma, Tatsuya Komatsu, Kansei Matsumoto, Hidetoshi Oya, Ryotaro Miura, Koji Yoshioka, Yoshikatsu Hoshi
2023	J	`jnl`	Audio Difference Learning for Audio Captioning. CoRR Tatsuya Komatsu, Yusuke Fujita, Kazuya Takeda, Tomoki Toda
2023	Misc	`conf`	Neural Diarization with Non-Autoregressive Intermediate Attractors. ICASSP Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa
2023	J	`jnl`	Neural Diarization with Non-autoregressive Intermediate Attractors. CoRR Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa
2023	J	`jnl`	PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions. CoRR Reo Shimizu, Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana
2023	A	`conf`	Target Vocabulary Recognition Based on Multi-Task Learning with Decomposed Teacher Sequences. INTERSPEECH Aoi Ito, Tatsuya Komatsu, Yusuke Fujita, Yusuke Kida
2022	J	`jnl`	Acoustic Event Detection with Classifier Chains. CoRR Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki, Tomoki Hayashi
2022	—	`conf`	Alternate Intermediate Conditioning with Syllable-Level and Character-Level Targets for Japanese ASR. SLT Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida
2022	A	`conf`	Better Intermediates Improve CTC Inference. INTERSPEECH Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe, Yusuke Kida
2022	J	`jnl`	Better Intermediates Improve CTC Inference. CoRR Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe, Yusuke Kida
2022	—	`conf`	Development of Estimation Systems of Calving Time Based on Time-Frequency Analysis for Ventral Tail Base Surface Temperature. ICCAIS Tatsuya Komatsu, Kansei Matsumoto, Ryotaro Miura, Hidetoshi Oya, Yoshikatsu Hoshi
2022	J	`jnl`	How Information on Acoustic Scenes and Sound Events Mutually Benefits Event Detection and Scene Classification Tasks. CoRR Keisuke Imoto, Yuka Komatsu, Shunsuke Tsubaki, Tatsuya Komatsu
2022	A	`conf`	InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR. INTERSPEECH Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida
2022	J	`jnl`	InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR. CoRR Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida
2022	—	`conf`	Interdecoder: using Attention Decoders as Intermediate Regularization for CTC-Based Speech Recognition. SLT Tatsuya Komatsu, Yusuke Fujita
2022	J	`jnl`	MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition. CoRR Jin Sakuma, Tatsuya Komatsu, Robin Scheibler
2022	J	`jnl`	Multi-sequence Intermediate Conditioning for CTC-based ASR. CoRR Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida
2022	Misc	`conf`	Non-Autoregressive ASR with Self-Conditioned Folded Encoders. ICASSP Tatsuya Komatsu
2022	J	`jnl`	Non-Autoregressive ASR with Self-Conditioned Folded Encoders. CoRR Tatsuya Komatsu
2022	Misc	`conf`	Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation. ICASSP Ibuki Kuroyanagi, Tatsuya Komatsu
2022	—	`conf`	Sound Event Localization and Detection with Pre-Trained Audio Spectrogram Transformer and Multichannel Seperation Network. DCASE Robin Scheibler, Tatsuya Komatsu, Yusuke Fujita, Michael Hentschel
2021	C	`conf`	A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. ASRU Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
2021	J	`jnl`	A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. CoRR Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
2021	A	`conf`	Acoustic Event Detection with Classifier Chains. Interspeech Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki, Tomoki Hayashi
2021	—	`conf`	Comparison of Low Complexity Self-Attention Mechanisms for Acoustic Event Detection. APSIPA ASC Tatsuya Komatsu, Robin Scheibler
2021	Misc	`conf`	Disentangled Speaker and Language Representations Using Mutual Information Minimization and Domain Adaptation for Cross-Lingual TTS. ICASSP Detai Xin, Tatsuya Komatsu, Shinnosuke Takamichi, Hiroshi Saruwatari
2021	J	`jnl`	Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers. CoRR Yusuke Kida, Tatsuya Komatsu, Masahito Togami
2021	—	`conf`	Multi-Source Domain Adaptation with Sinkhorn Barycenter. EUSIPCO Tatsuya Komatsu, Tomoko Matsui, Junbin Gao
2021	—	`conf`	Multichannel Separation and Classification of Sound Events. EUSIPCO Robin Scheibler, Tatsuya Komatsu, Masahito Togami
2021	A	`conf`	Relaxing the Conditional Independence Assumption of CTC-Based ASR by Conditioning on Intermediate Predictions. Interspeech Jumon Nozaki, Tatsuya Komatsu
2021	J	`jnl`	Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions. CoRR Jumon Nozaki, Tatsuya Komatsu
2020	—	`conf`	Computer-Resource-Aware Deep Speech Separation with a Run-Time-Specified Number of BLSTM Layers. APSIPA Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Kazuyoshi Yoshii, Tatsuya Kawahara
2020	—	`conf`	Conformer-Based Sound Event Detection with Semi-Supervised Learning and Data Augmentation. DCASE Koichi Miyazaki, Tatsuya Komatsu, Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda
2020	Misc	`conf`	Consistency-Aware Multi-Channel Speech Enhancement Using Deep Neural Networks. ICASSP Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
2020	J	`jnl`	Consistency-aware multi-channel speech enhancement using deep neural networks. CoRR Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
2020	J	`jnl`	Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation. CoRR Tsubasa Takahashi, Shun Takagi, Hajime Ono, Tatsuya Komatsu
2020	—	`ed.`	Proceedings of 5th the Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE 2020), Tokyo, Japan (full virtual), November 2-4, 2020 DCASE Nobutaka Ono, Noboru Harada, Yohei Kawaguchi, Annamaria Mesaros, Keisuke Imoto, Yuma Koizumi, Tatsuya Komatsu
2020	—	`conf`	Robust Acoustic Scene Classification to Multiple Devices Using Maximum Classifier Discrepancy and Knowledge Distillation. EUSIPCO Saori Takeyama, Tatsuya Komatsu, Koichi Miyazaki, Masahito Togami, Shunsuke Ono
2020	Misc	`conf`	Scene-Dependent Acoustic Event Detection with Scene Conditioning and Fake-Scene-Conditioned Loss. ICASSP Tatsuya Komatsu, Keisuke Imoto, Masahito Togami
2020	—	`conf`	Sound Event Localization and Detection Using Convolutional Recurrent Neural Networks and Gated Linear Units. EUSIPCO Tatsuya Komatsu, Masahito Togami, Tsubasa Takahashi
2020	Misc	`conf`	Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function. ICASSP Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Yu Nakagome
2020	Misc	`conf`	Weakly-Supervised Sound Event Detection with Self-Attention. ICASSP Koichi Miyazaki, Tatsuya Komatsu, Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda
2019	J	`jnl`	Bayesian Non-Parametric Multi-Source Modelling Based Determined Blind Source Separation. CoRR Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
2019	Misc	`conf`	Bayesian Non-parametric Multi-source Modelling Based Determined Blind Source Separation. ICASSP Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
2019	—	`conf`	Fast Convergence Algorithm for State-Space Model Based Speech Dereverberation by Multi-Channel Non-Negative Matrix Factorization. WASPAA Masahito Togami, Tatsuya Komatsu
2019	J	`jnl`	Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning. CoRR Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
2019	A	`conf`	Multichannel Loss Function for Supervised Speech Source Separation by Mask-Based Beamforming. INTERSPEECH Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
2019	J	`jnl`	Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming. CoRR Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
2019	J	`jnl`	Overview of Tasks and Investigation of Subjective Evaluation Methods in Environmental Sound Synthesis and Conversion. CoRR Yuki Okamoto, Keisuke Imoto, Tatsuya Komatsu, Shinnosuke Takamichi, Takumi Yagyu, Ryosuke Yamanishi, Yoichi Yamashita
2019	Misc	`conf`	Scene-dependent Anomalous Acoustic-event Detection Based on Conditional Wavenet and I-vector. ICASSP Tatsuya Komatsu, Tomoki Hayashi, Reishi Kondo, Tomoki Toda, Kazuya Takeda
2019	J	`jnl`	Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function. CoRR Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Yu Nakagome
2019	A	`conf`	Variational Bayesian Multi-Channel Speech Dereverberation Under Noisy Environments with Probabilistic Convolutive Transfer Function. INTERSPEECH Masahito Togami, Tatsuya Komatsu
2018	J	`jnl`	A Stereo Wind-Noise Suppressor with Null Beamforming and Frequency-Domain Noise Averaging. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Masanori Kato, Akihiko Sugiyama, Tatsuya Komatsu
2018	—	`conf`	Anomalous Sound Event Detection Based on WaveNet. EUSIPCO Tomoki Hayashi, Tatsuya Komatsu, Reishi Kondo, Tomoki Toda, Kazuya Takeda
2018	—	`conf`	Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning. EUSIPCO Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo
2018	—	`conf`	Weakly Labeled Learning Using BLSTM-CTC for Sound Event Detection. APSIPA Taiki Matsuyoshi, Tatsuya Komatsu, Reishi Kondo, Takeshi Yamada, Shoji Makino
2017	—	`conf`	An acoustic monitoring system and its field trials. APSIPA Tatsuya Komatsu, Masahiro Tani, Takahiro Toizumi, Chaitanya Narisetty, Masanori Kato, Yumi Arai, Osamu Hoshuyama, Yuzo Senda, Reishi Kondo
2017	Misc	`conf`	Detection of anomaly acoustic scenes based on a temporal dissimilarity model. ICASSP Tatsuya Komatsu, Reishi Kondo
2016	—	`conf`	Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries. DCASE Tatsuya Komatsu, Takahiro Toizumi, Reishi Kondo, Yuzo Senda
2016	Misc	`conf`	Acoustic event detection based on non-negative matrix factorization with mixtures of local dictionaries and activation aggregation. ICASSP Tatsuya Komatsu, Yuzo Senda, Reishi Kondo
2013	Misc	`conf`	Computationally efficient single channel dereverberation based on complementary wiener filter. ICASSP Kazunobu Kondo, Yu Takahashi, Tatsuya Komatsu, Takanori Nishino, Kazuya Takeda
2013	Misc	`conf`	Modeling head-related transfer functions via spatial-temporal Gaussian process. ICASSP Tatsuya Komatsu, Takanori Nishino, Gareth W. Peters, Tomoko Matsui, Kazuya Takeda
1998	J	`jnl`	A 240-Mbps, 1-W CMOS EPRML read-channel LSI chip using an interleaved subranging pipeline A/D converter. IEEE J. Solid State Circuits Tatsuji Matsuura, Takashi Nara, Tatsuya Komatsu, Eiki Imaizumi, Toshihiro Matsutsuru, Ryutaro Horita, Haruto Katsu, Shintaro Suzumura, Kazuo Sato