Yuma Koizumi

Publication Activity (10 Years)

Years Active: 2014-2023
Publications (10 Years): 86

Top Topics

Speech Enhancement

Anomaly Detection

Condition Monitoring

Top Venues

Publications

Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, Ankur Bapna
LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus. INTERSPEECH (2023)
Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Yu Zhang, Wei Han, Ankur Bapna, Michiel Bacchiani
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations. CoRR (2023)
Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Yohei Kawaguchi
Description and Discussion on DCASE 2023 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. CoRR (2023)
Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, Ankur Bapna
LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus. CoRR (2023)
Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Yu Zhang, Wei Han, Ankur Bapna, Michiel Bacchiani
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations. WASPAA (2023)
Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani
SNRi Target Training for Joint Speech Enhancement and Recognition. INTERSPEECH (2022)
Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques. DCASE (2022)
Arun Narayanan, James Walker, Sankaran Panchapagesan, Nathan Howard, Yuma Koizumi
Mask scalar prediction for improving robust automatic speech recognition. CoRR (2022)
Arun Narayanan, James Walker, Sankaran Panchapagesan, Nathan Howard, Yuma Koizumi
Learning Mask Scalars for Improved Robust Automatic Speech Recognition. SLT (2022)
Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques. CoRR (2022)
Yuma Koizumi, Kohei Yatabe, Heiga Zen, Michiel Bacchiani
WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration. CoRR (2022)
Yuma Koizumi, Kohei Yatabe, Heiga Zen, Michiel Bacchiani
Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration. SLT (2022)
Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani
SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping. CoRR (2022)
Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani
SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping. INTERSPEECH (2022)
Koichi Saito, Tomohiko Nakamura, Kohei Yatabe, Yuma Koizumi, Hiroshi Saruwatari
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method. EUSIPCO (2021)
Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement. CoRR (2021)
Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi, Noboru Harada, Daisuke Niizumi, Kota Dohi, Ryo Tanabe, Harsh Purohit, Takashi Endo
Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions. CoRR (2021)
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Deep Griffin-Lim Iteration: Trainable Iterative Phase Reconstruction Using Neural Network. IEEE J. Sel. Top. Signal Process. 15 (1) (2021)
Takuya Fujimura, Yuma Koizumi, Kohei Yatabe, Ryoichi Miyazaki
Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech. EUSIPCO (2021)
Koichi Saito, Tomohiko Nakamura, Kohei Yatabe, Yuma Koizumi, Hiroshi Saruwatari
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method. CoRR (2021)
Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani
SNRi Target Training for Joint Speech Enhancement and Recognition. CoRR (2021)
Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi, Noboru Harada, Daisuke Niizumi, Kota Dohi, Ryo Tanabe, Harsh Purohit, Takashi Endo
Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Detection for Machine Condition Monitoring Under Domain Shifted Conditions. DCASE (2021)
Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement. WASPAA (2021)
Daiki Takeuchi, Yuma Koizumi, Yasunori Ohishi, Noboru Harada, Kunio Kashino
Effects of Word-Frequency Based Pre- and Post- Processings for Audio Captioning. DCASE (2020)
Masahiro Yasuda, Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Keisuke Imoto
Sound Event Localization Based on Sound Intensity Vector Refined by Dnn-Based Denoising and Source Separation. ICASSP (2020)
Daiki Takeuchi, Yuma Koizumi, Yasunori Ohishi, Noboru Harada, Kunio Kashino
Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning. CoRR (2020)
Masahiro Yasuda, Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Keisuke Imoto
Sound Event Localization based on Sound Intensity Vector Refined By DNN-Based Denoising and Source Separation. CoRR (2020)
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Phase Reconstruction Based On Recurrent Phase Unwrapping With Deep Neural Networks. ICASSP (2020)
Masaki Kawanaka, Yuma Koizumi, Ryoichi Miyazaki, Kohei Yatabe
Stable Training of DNN for Speech Enhancement based on Perceptually-Motivated Black-Box Cost Function. CoRR (2020)
Yuma Koizumi, Kohei Yatabe, Marc Delcroix, Yoshiki Masuyama, Daiki Takeuchi
Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention. ICASSP (2020)
Yuma Koizumi, Kohei Yatabe, Marc Delcroix, Yoshiki Masuyama, Daiki Takeuchi
Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention. CoRR (2020)
Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi, Hiroaki Ito, Keisuke Kinoshita, Shoko Araki
Listen to What You Want: Neural Network-Based Universal Sound Selector. INTERSPEECH (2020)
Yuma Koizumi, Ryo Masumura, Kyosuke Nishida, Masahiro Yasuda, Shoichiro Saito
A Transformer-based Audio Captioning Model with Keyword Estimation. CoRR (2020)
Yuma Koizumi, Yasunori Ohishi, Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda
Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval. CoRR (2020)
Yuma Koizumi, Masahiro Yasuda, Shin Murata, Shoichiro Saito, Hisashi Uematsu, Noboru Harada
SPIDERnet: Attention Network For One-Shot Anomaly Detection In Sounds. ICASSP (2020)
Masahiro Yasuda, Yasunori Ohishi, Yuma Koizumi, Noboru Harada
Crossmodal Sound Retrieval Based on Specific Target Co-Occurrence Denoted with Weak Labels. INTERSPEECH (2020)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Real-Time Speech Enhancement Using Equilibriated RNN. ICASSP (2020)
Yuma Koizumi, Yohei Kawaguchi, Keisuke Imoto, Toshiki Nakamura, Yuki Nikaido, Ryo Tanabe, Harsh Purohit, Kaori Suefusa, Takashi Endo, Masahiro Yasuda, Noboru Harada
Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. CoRR (2020)
Keisuke Imoto, Noriyuki Tonami, Yuma Koizumi, Masahiro Yasuda, Ryosuke Yamanishi, Yoichi Yamashita
Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels. ICASSP (2020)
Keisuke Imoto, Noriyuki Tonami, Yuma Koizumi, Masahiro Yasuda, Ryosuke Yamanishi, Yoichi Yamashita
Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels. CoRR (2020)
Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi, Hiroaki Ito, Keisuke Kinoshita, Shoko Araki
Listen to What You Want: Neural Network-based Universal Sound Selector. CoRR (2020)
Masaki Kawanaka, Yuma Koizumi, Ryoichi Miyazaki, Kohei Yatabe
Stable Training of Dnn for Speech Enhancement Based on Perceptually-Motivated Black-Box Cost Function. ICASSP (2020)
Yuma Koizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino
The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation. CoRR (2020)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Real-time speech enhancement using equilibriated RNN. CoRR (2020)
Yuma Koizumi, Yohei Kawaguchi, Keisuke Imoto, Toshiki Nakamura, Yuki Nikaido, Ryo Tanabe, Harsh Purohit, Kaori Suefusa, Takashi Endo, Masahiro Yasuda, Noboru Harada
Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. DCASE (2020)
Yuma Koizumi, Ryo Masumura, Kyosuke Nishida, Masahiro Yasuda, Shoichiro Saito
A Transformer-Based Audio Captioning Model with Keyword Estimation. INTERSPEECH (2020)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Invertible DNN-Based Nonlinear Time-Frequency Transform for Speech Enhancement. ICASSP (2020)
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Phase reconstruction based on recurrent phase unwrapping with deep neural networks. CoRR (2020)
Ryo Masumura, Kiyoaki Matsui, Yuma Koizumi, Takaaki Fukutomi, Takanobu Oba, Yushi Aono
Context-Aware Neural Voice Activity Detection Using Auxiliary Networks for Phoneme Recognition, Speech Enhancement and Acoustic Scene Classification. EUSIPCO (2019)
Yuta Kawachi, Yuma Koizumi, Shin Murata, Noboru Harada
A Two-class Hyper-spherical Autoencoder for Supervised Anomaly Detection. ICASSP (2019)
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Deep Griffin-Lim Iteration. CoRR (2019)
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Noboru Harada, Keisuke Imoto
ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection. WASPAA (2019)
Masataka Yamaguchi, Yuma Koizumi, Noboru Harada
AdaFlow: Domain-adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-domain Translation. ICASSP (2019)
Yuma Koizumi, Shoichiro Saito, Masataka Yamaguchi, Shin Murata, Noboru Harada
Batch Uniformization for Minimizing Maximum Anomaly Score of Dnn-Based Anomaly Detection in Sounds. WASPAA (2019)
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Noboru Harada, Keisuke Imoto
ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection. CoRR (2019)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Invertible DNN-based nonlinear time-frequency transform for speech enhancement. CoRR (2019)
Shin Murata, Yuma Koizumi, Noboru Harada
Finding Low-Dimensional Dynamical Structure Through Variational Auto-Encoding Dynamic Mode Decomposition. MLSP (2019)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Data-driven Design of Perfect Reconstruction Filterbank for DNN-based Sound Source Enhancement. ICASSP (2019)
Daiki Takeuchi, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Data-driven design of perfect reconstruction filterbank for DNN-based sound source enhancement. CoRR (2019)
Yuma Koizumi, Shin Murata, Noboru Harada, Shoichiro Saito, Hisashi Uematsu
SNIPER: Few-shot Learning for Anomaly Detection to Minimize False-negative Rate with Ensured True-positive Rate. ICASSP (2019)
Yuma Koizumi, Shoichiro Saito, Masataka Yamaguchi, Shin Murata, Noboru Harada
Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds. CoRR (2019)
Luca Mazzon, Yuma Koizumi, Masahiro Yasuda, Noboru Harada
First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation. DCASE (2019)
Yoshiki Masuyama, Kohei Yatabe, Yuma Koizumi, Yasuhiro Oikawa, Noboru Harada
Deep Griffin-Lim Iteration. ICASSP (2019)
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Yuta Kawachi, Noboru Harada
Unsupervised Detection of Anomalous Sound Based on Deep Learning and the Neyman-Pearson Lemma. IEEE ACM Trans. Audio Speech Lang. Process. 27 (1) (2019)
Luca Mazzon, Yuma Koizumi, Masahiro Yasuda, Noboru Harada
First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation. CoRR (2019)
Yuma Koizumi, Noboru Harada, Yoichi Haneda
Trainable Adaptive Window Switching for Speech Enhancement. ICASSP (2019)
Masahiro Yasuda, Yuma Koizumi, Luca Mazzon, Shoichiro Saito, Hisashi Uematsu
DOA Estimation by DNN-based Denoising and Dereverberation from Sound Intensity Vector. CoRR (2019)
Masataka Yamaguchi, Yuma Koizumi, Noboru Harada
AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation. CoRR (2018)
Yuma Koizumi, Noboru Harada, Yoichi Haneda, Yusuke Hioka, Kazunori Kobayashi
End-to-End Sound Source Enhancement Using Deep Neural Network in the Modified Discrete Cosine Transform Domain. ICASSP (2018)
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Yuta Kawachi, Noboru Harada
Unsupervised Detection of Anomalous Sound based on Deep Learning and the Neyman-Pearson Lemma. CoRR (2018)
Yuta Kawachi, Yuma Koizumi, Noboru Harada
Complementary Set Variational Autoencoder for Supervised Anomaly Detection. ICASSP (2018)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Yoichi Haneda
DNN-Based Source Enhancement to Increase Objective Sound Quality Assessment Score. IEEE ACM Trans. Audio Speech Lang. Process. 26 (10) (2018)
Yuma Koizumi, Noboru Harada, Yoichi Haneda
Trainable Adaptive Window Switching for Speech Enhancement. CoRR (2018)
Sota Nishiguchi, Yuma Koizumi, Noboru Harada, Katunobu Itou
DNN-Based Near- and Far-Field Source Separation Using Spherical-Harmonic-Analysis-Based Acoustic Features. IWAENC (2018)
Yuma Koizumi, Shoichiro Saito, Suehiro Shimauchi, Kazunori Kobayashi, Noboru Harada
Distant Noise Reduction Based on Multi-delay Noise Model Using Distributed Microphone Array. EUSIPCO (2018)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Yoichi Haneda
DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Score. CoRR (2018)
Kenta Niwa, Yuma Koizumi, Tomoko Kawase, Kazunori Kobayashi, Yusuke Hioka
Supervised source enhancement composed of nonnegative auto-encoders and complementarity subtraction. ICASSP (2017)
Yuma Koizumi, Shoichiro Saito, Hisashi Uematsu, Noboru Harada
Optimizing acoustic feature extractor for anomalous sound detection based on Neyman-Pearson lemma. EUSIPCO (2017)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Hitoshi Ohmuro
Informative Acoustic Feature Selection to Maximize Mutual Information for Collecting Target Sources. IEEE ACM Trans. Audio Speech Lang. Process. 25 (4) (2017)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Yoichi Haneda
DNN-based source enhancement self-optimized by reinforcement learning using sound quality measurements. ICASSP (2017)
Suehiro Shimauchi, Shinya Kudo, Yuma Koizumi, Ken'ichi Furuya
On relationships between amplitude and phase of short-time Fourier transform. ICASSP (2017)
Kenta Niwa, Yuma Koizumi, Kazunori Kobayashi, Hisashi Uematsu
Binaural sound generation corresponding to omnidirectional video view using angular region-wise source enhancement. ICASSP (2016)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Hitoshi Ohmuro
Integrated approach of feature extraction and sound source enhancement based on maximization of mutual information. ICASSP (2016)
Kenta Niwa, Yuma Koizumi, Tomoko Kawase, Kazunori Kobayashi, Yusuke Hioka
Pinpoint extraction of distant sound source based on DNN mapping from multiple beamforming outputs to prior SNR. ICASSP (2016)
Yuma Koizumi, Yuki Ijichi, Hisaya Tanaka, Ayumi Otera, Kayoko Takahashi, Michinari Fukuda, Noriyoshi Asai
Effective approach to character input for novice BCI users. APSITT (2015)
Yuma Koizumi, Kenta Niwa, Yusuke Hioka, Kazunori Kobayashi, Hitoshi Ohmuro
Informative acoustic feature selection on microphone array wiener filtering for collecting target source on sports ground. WASPAA (2015)
Yuma Koizumi, Katunobu Itou
Intra-note segmentation via sticky HMM with DP emission. ICASSP (2014)