default search action
Tatsuya Komatsu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c43]Tatsuya Komatsu, Yusuke Fujita, Kazuya Takeda, Tomoki Toda:
Audio Difference Learning for Audio Captioning. ICASSP 2024: 1456-1460 - [c42]Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita:
Keep Decoding Parallel With Effective Knowledge Distillation From Language Models To End-To-End Speech Recognisers. ICASSP 2024: 10876-10880 - [c41]Reo Shimizu, Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana:
PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions. ICASSP 2024: 12672-12676 - [i27]Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita:
Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers. CoRR abs/2401.11700 (2024) - [i26]Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu:
Universal Score-based Speech Enhancement with High Content Preservation. CoRR abs/2406.12194 (2024) - [i25]Yusuke Fujita, Tatsuya Komatsu:
Audio Fingerprinting with Holographic Reduced Representations. CoRR abs/2406.13139 (2024) - [i24]Taichi Nishimura, Shota Nakada, Hokuto Munakata, Tatsuya Komatsu:
Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection. CoRR abs/2408.02901 (2024) - [i23]Shota Nakada, Taichi Nishimura, Hokuto Munakata, Masayoshi Kondo, Tatsuya Komatsu:
DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information. CoRR abs/2409.11729 (2024) - [i22]Hokuto Munakata, Taichi Nishimura, Shota Nakada, Tatsuya Komatsu:
Language-based Audio Moment Retrieval. CoRR abs/2409.15672 (2024) - [i21]Yuchi Ishikawa, Tatsuya Komatsu, Yoshimitsu Aoki:
Pre-training with Synthetic Patterns for Audio. CoRR abs/2410.00511 (2024) - 2023
- [c40]Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa:
Neural Diarization with Non-Autoregressive Intermediate Attractors. ICASSP 2023: 1-5 - [c39]Hiroto Noma, Tatsuya Komatsu, Kansei Matsumoto, Hidetoshi Oya, Ryotaro Miura, Koji Yoshioka, Yoshikatsu Hoshi:
Analysis of Biological Data of Cows and Development of Detection Systems for Calving Phase. IECON 2023: 1-6 - [c38]Aoi Ito, Tatsuya Komatsu, Yusuke Fujita, Yusuke Kida:
Target Vocabulary Recognition Based on Multi-Task Learning with Decomposed Teacher Sequences. INTERSPEECH 2023: 1254-1258 - [i20]Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa:
Neural Diarization with Non-autoregressive Intermediate Attractors. CoRR abs/2303.06806 (2023) - [i19]Reo Shimizu, Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana:
PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions. CoRR abs/2309.08140 (2023) - [i18]Tatsuya Komatsu, Yusuke Fujita, Kazuya Takeda, Tomoki Toda:
Audio Difference Learning for Audio Captioning. CoRR abs/2309.08141 (2023) - 2022
- [c37]Robin Scheibler, Tatsuya Komatsu, Yusuke Fujita, Michael Hentschel:
Sound Event Localization and Detection with Pre-Trained Audio Spectrogram Transformer and Multichannel Seperation Network. DCASE 2022 - [c36]Ibuki Kuroyanagi, Tatsuya Komatsu:
Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation. ICASSP 2022: 3263-3267 - [c35]Tatsuya Komatsu:
Non-Autoregressive ASR with Self-Conditioned Folded Encoders. ICASSP 2022: 7427-7431 - [c34]Tatsuya Komatsu, Kansei Matsumoto, Ryotaro Miura, Hidetoshi Oya, Yoshikatsu Hoshi:
Development of Estimation Systems of Calving Time Based on Time-Frequency Analysis for Ventral Tail Base Surface Temperature. ICCAIS 2022: 217-222 - [c33]Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe
, Yusuke Kida:
Better Intermediates Improve CTC Inference. INTERSPEECH 2022: 4965-4969 - [c32]Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida:
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR. INTERSPEECH 2022: 5140-5144 - [c31]Tatsuya Komatsu, Yusuke Fujita:
Interdecoder: using Attention Decoders as Intermediate Regularization for CTC-Based Speech Recognition. SLT 2022: 46-51 - [c30]Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida:
Alternate Intermediate Conditioning with Syllable-Level and Character-Level Targets for Japanese ASR. SLT 2022: 76-83 - [i17]Jin Sakuma, Tatsuya Komatsu, Robin Scheibler:
MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition. CoRR abs/2202.08456 (2022) - [i16]Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki, Tomoki Hayashi:
Acoustic Event Detection with Classifier Chains. CoRR abs/2202.08470 (2022) - [i15]Tatsuya Komatsu:
Non-Autoregressive ASR with Self-Conditioned Folded Encoders. CoRR abs/2202.08474 (2022) - [i14]Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida:
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR. CoRR abs/2204.00174 (2022) - [i13]Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida:
Multi-sequence Intermediate Conditioning for CTC-based ASR. CoRR abs/2204.00175 (2022) - [i12]Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe, Yusuke Kida:
Better Intermediates Improve CTC Inference. CoRR abs/2204.00176 (2022) - [i11]Keisuke Imoto, Yuka Komatsu, Shunsuke Tsubaki, Tatsuya Komatsu:
How Information on Acoustic Scenes and Sound Events Mutually Benefits Event Detection and Scene Classification Tasks. CoRR abs/2204.02279 (2022) - 2021
- [c29]Tatsuya Komatsu, Robin Scheibler:
Comparison of Low Complexity Self-Attention Mechanisms for Acoustic Event Detection. APSIPA ASC 2021: 1139-1143 - [c28]Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. ASRU 2021: 47-54 - [c27]Robin Scheibler, Tatsuya Komatsu, Masahito Togami:
Multichannel Separation and Classification of Sound Events. EUSIPCO 2021: 1035-1039 - [c26]Tatsuya Komatsu, Tomoko Matsui, Junbin Gao:
Multi-Source Domain Adaptation with Sinkhorn Barycenter. EUSIPCO 2021: 1371-1375 - [c25]Detai Xin, Tatsuya Komatsu, Shinnosuke Takamichi, Hiroshi Saruwatari:
Disentangled Speaker and Language Representations Using Mutual Information Minimization and Domain Adaptation for Cross-Lingual TTS. ICASSP 2021: 6608-6612 - [c24]Tatsuya Komatsu, Shinji Watanabe
Acoustic Event Detection with Classifier Chains. Interspeech 2021: 601-605 - [c23]Jumon Nozaki, Tatsuya Komatsu:
Relaxing the Conditional Independence Assumption of CTC-Based ASR by Conditioning on Intermediate Predictions. Interspeech 2021: 3735-3739 - [i10]Jumon Nozaki, Tatsuya Komatsu:
Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions. CoRR abs/2104.02724 (2021) - [i9]Yusuke Kida, Tatsuya Komatsu, Masahito Togami:
Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers. CoRR abs/2104.10328 (2021) - [i8]Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe:
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation. CoRR abs/2110.05249 (2021) - 2020
- [c22]Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Kazuyoshi Yoshii, Tatsuya Kawahara:
Computer-Resource-Aware Deep Speech Separation with a Run-Time-Specified Number of BLSTM Layers. APSIPA 2020: 788-793 - [c21]Koichi Miyazaki, Tatsuya Komatsu, Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda:
Conformer-Based Sound Event Detection with Semi-Supervised Learning and Data Augmentation. DCASE 2020: 100-104 - [c20]Saori Takeyama, Tatsuya Komatsu, Koichi Miyazaki, Masahito Togami, Shunsuke Ono:
Robust Acoustic Scene Classification to Multiple Devices Using Maximum Classifier Discrepancy and Knowledge Distillation. EUSIPCO 2020: 36-40 - [c19]Tatsuya Komatsu, Masahito Togami, Tsubasa Takahashi:
Sound Event Localization and Detection Using Convolutional Recurrent Neural Networks and Gated Linear Units. EUSIPCO 2020: 41-45 - [c18]Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Yu Nakagome:
Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function. ICASSP 2020: 56-60 - [c17]Koichi Miyazaki, Tatsuya Komatsu, Tomoki Hayashi, Shinji Watanabe
Weakly-Supervised Sound Event Detection with Self-Attention. ICASSP 2020: 66-70 - [c16]Tatsuya Komatsu, Keisuke Imoto, Masahito Togami:
Scene-Dependent Acoustic Event Detection with Scene Conditioning and Fake-Scene-Conditioned Loss. ICASSP 2020: 646-650 - [c15]Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu:
Consistency-Aware Multi-Channel Speech Enhancement Using Deep Neural Networks. ICASSP 2020: 821-825 - [e1]Nobutaka Ono, Noboru Harada, Yohei Kawaguchi, Annamaria Mesaros, Keisuke Imoto, Yuma Koizumi, Tatsuya Komatsu:
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. 2020, ISBN 978-4-600-00566-5 [contents] - [i7]Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu:
Consistency-aware multi-channel speech enhancement using deep neural networks. CoRR abs/2002.05831 (2020) - [i6]Tsubasa Takahashi, Shun Takagi, Hajime Ono, Tatsuya Komatsu:
Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation. CoRR abs/2006.11204 (2020)
2010 – 2019
- 2019
- [c14]Chaitanya Narisetty
Bayesian Non-parametric Multi-source Modelling Based Determined Blind Source Separation. ICASSP 2019: 111-115 - [c13]Tatsuya Komatsu, Tomoki Hayashi, Reishi Kondo, Tomoki Toda, Kazuya Takeda:
Scene-dependent Anomalous Acoustic-event Detection Based on Conditional Wavenet and I-vector. ICASSP 2019: 870-874 - [c12]Masahito Togami, Tatsuya Komatsu:
Variational Bayesian Multi-Channel Speech Dereverberation Under Noisy Environments with Probabilistic Convolutive Transfer Function. INTERSPEECH 2019: 106-110 - [c11]Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu:
Multichannel Loss Function for Supervised Speech Source Separation by Mask-Based Beamforming. INTERSPEECH 2019: 2708-2712 - [c10]Masahito Togami, Tatsuya Komatsu:
Fast Convergence Algorithm for State-Space Model Based Speech Dereverberation by Multi-Channel Non-Negative Matrix Factorization. WASPAA 2019: 244-248 - [i5]Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo:
Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning. CoRR abs/1904.02852 (2019) - [i4]Chaitanya Narisetty, Tatsuya Komatsu, Reishi Kondo:
Bayesian Non-Parametric Multi-Source Modelling Based Determined Blind Source Separation. CoRR abs/1904.03787 (2019) - [i3]Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu:
Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming. CoRR abs/1907.04984 (2019) - [i2]Yuki Okamoto, Keisuke Imoto, Tatsuya Komatsu, Shinnosuke Takamichi, Takumi Yagyu, Ryosuke Yamanishi, Yoichi Yamashita:
Overview of Tasks and Investigation of Subjective Evaluation Methods in Environmental Sound Synthesis and Conversion. CoRR abs/1908.10055 (2019) - [i1]Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu, Yu Nakagome:
Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function. CoRR abs/1911.04228 (2019) - 2018
- [j2]Masanori Kato, Akihiko Sugiyama, Tatsuya Komatsu:
A Stereo Wind-Noise Suppressor with Null Beamforming and Frequency-Domain Noise Averaging. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 101-A(10): 1631-1637 (2018) - [c9]Taiki Matsuyoshi, Tatsuya Komatsu, Reishi Kondo, Takeshi Yamada, Shoji Makino
Weakly Labeled Learning Using BLSTM-CTC for Sound Event Detection. APSIPA 2018: 1918-1923 - [c8]Chaitanya Narisetty
Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning. EUSIPCO 2018: 847-851 - [c7]Tomoki Hayashi, Tatsuya Komatsu, Reishi Kondo, Tomoki Toda
Anomalous Sound Event Detection Based on WaveNet. EUSIPCO 2018: 2494-2498 - 2017
- [c6]Tatsuya Komatsu, Masahiro Tani, Takahiro Toizumi, Chaitanya Narisetty
An acoustic monitoring system and its field trials. APSIPA 2017: 1341-1346 - [c5]Tatsuya Komatsu, Reishi Kondo:
Detection of anomaly acoustic scenes based on a temporal dissimilarity model. ICASSP 2017: 376-380 - 2016
- [c4]Tatsuya Komatsu, Takahiro Toizumi, Reishi Kondo, Yuzo Senda:
Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries. DCASE 2016: 45-49 - [c3]Tatsuya Komatsu, Yuzo Senda, Reishi Kondo:
Acoustic event detection based on non-negative matrix factorization with mixtures of local dictionaries and activation aggregation. ICASSP 2016: 2259-2263 - 2013
- [c2]Tatsuya Komatsu, Takanori Nishino, Gareth W. Peters
Modeling head-related transfer functions via spatial-temporal Gaussian process. ICASSP 2013: 301-305 - [c1]Kazunobu Kondo, Yu Takahashi, Tatsuya Komatsu, Takanori Nishino, Kazuya Takeda:
Computationally efficient single channel dereverberation based on complementary wiener filter. ICASSP 2013: 7452-7456
1990 – 1999
- 1998
- [j1]Tatsuji Matsuura, Takashi Nara, Tatsuya Komatsu, Eiki Imaizumi, Toshihiro Matsutsuru, Ryutaro Horita, Haruto Katsu, Shintaro Suzumura, Kazuo Sato:
A 240-Mbps, 1-W CMOS EPRML read-channel LSI chip using an interleaved subranging pipeline A/D converter. IEEE J. Solid State Circuits 33(11): 1840-1850 (1998)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 00:11 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: