Yuma Koizumi

发表

First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation pdf

Masahiro Yasuda, Noboru Harada, Yuma Koizumi, 2019, DCASE.

Trainable Adaptive Window Switching for Speech Enhancement

Noboru Harada, Youichi Haneda, Yuma Koizumi, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration

H. Zen, M. Bacchiani, K. Yatabe, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Effect of spectrogram resolution on deep-neural-network-based speech enhancement

Yasuhiro Oikawa, Yuma Koizumi, Daiki Takeuchi, 2020, Acoustical Science and Technology.

SNIPER: Few-shot Learning for Anomaly Detection to Minimize False-negative Rate with Ensured True-positive Rate

Noboru Harada, Yuma Koizumi, Shoichiro Saito, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sound Event Localization Based on Sound Intensity Vector Refined by Dnn-Based Denoising and Source Separation

Masahiro Yasuda, Yuma Koizumi, Shoichiro Saito, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SOUND EVENT LOCALIZATION AND DETECTION USING FOA DOMAIN SPATIAL AUGMENTATION Technical Report

N. Harada, Luca Mazzon, Yuma Koizumi, 2019 .

Listen to What You Want: Neural Network-based Universal Sound Selector

Shoko Araki, Marc Delcroix, Keisuke Kinoshita, 2020, INTERSPEECH.

DNN-Based Near- and Far-Field Source Separation Using Spherical-Harmonic-Analysis-Based Acoustic Features

Katunobu Itou, Noboru Harada, Yuma Koizumi, 2018, 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC).

Informative Acoustic Feature Selection to Maximize Mutual Information for Collecting Target Sources

Yusuke Hioka, Kazunori Kobayashi, Kenta Niwa, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Integrated approach of feature extraction and sound source enhancement based on maximization of mutual information

Yusuke Hioka, Kazunori Kobayashi, Kenta Niwa, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Informative acoustic feature selection on microphone array wiener filtering for collecting target source on sports ground

Yusuke Hioka, Kazunori Kobayashi, Kenta Niwa, 2015, 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Intra-note segmentation via sticky HMM with DP emission

Katunobu Itou, Yuma Koizumi, K. Itou, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention

Marc Delcroix, Daiki Takeuchi, Yoshiki Masuyama, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DNN-Based Source Enhancement to Increase Objective Sound Quality Assessment Score

Yusuke Hioka, Kazunori Kobayashi, Kenta Niwa, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech

K. Yatabe, Ryoichi Miyazaki, Yuma Koizumi, 2021, 2021 29th European Signal Processing Conference (EUSIPCO).

Crossmodal Sound Retrieval Based on Specific Target Co-Occurrence Denoted with Weak Labels

Masahiro Yasuda, Yasunori Ohishi, Noboru Harada, 2020, INTERSPEECH.

A Transformer-based Audio Captioning Model with Keyword Estimation

Kyosuke Nishida, Ryo Masumura, Yuma Koizumi, 2020, INTERSPEECH.

DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement

Scott Wisdom, John R. Hershey, Michiel Bacchiani, 2021, 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels

Ryosuke Yamanishi, Masahiro Yasuda, Keisuke Imoto, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection

Yuma Koizumi, Shoichiro Saito, Noboru Harada, 2019, 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval pdf

Masahiro Yasuda, Yasunori Ohishi, Daiki Takeuchi, 2020, ArXiv.

SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping

H. Zen, M. Bacchiani, Nanxin Chen, 2022, INTERSPEECH.

The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation pdf

Kunio Kashino, Yasunori Ohishi, Daiki Takeuchi, 2020, ArXiv.

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

H. Zen, M. Bacchiani, Ankur Bapna, 2023, ArXiv.

Batch Uniformization for Minimizing Maximum Anomaly Score of Dnn-Based Anomaly Detection in Sounds

Noboru Harada, Shoichiro Saito, Masataka Yamaguchi, 2019, 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

End-to-End Sound Source Enhancement Using Deep Neural Network in the Modified Discrete Cosine Transform Domain

Yusuke Hioka, Kazunori Kobayashi, Noboru Harada, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions pdf

Yohei Kawaguchi, Yuma Koizumi, Noboru Harada, 2021, DCASE.

Complementary Set Variational Autoencoder for Supervised Anomaly Detection

Noboru Harada, Yuma Koizumi, Yuta Kawachi, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DNN-based source enhancement self-optimized by reinforcement learning using sound quality measurements

Yusuke Hioka, Kazunori Kobayashi, Youichi Haneda, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Takashi Endo, Y. Kawaguchi, N. Harada, 2020, DCASE.

Finding Low-Dimensional Dynamical Structure Through Variational Auto-Encoding Dynamic Mode Decomposition

Yuma Koizumi, Noboru Harada, Shin Murata, 2019, 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP).

Phase Reconstruction Based On Recurrent Phase Unwrapping With Deep Neural Networks

Yasuhiro Oikawa, Yoshiki Masuyama, Kohei Yatabe, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning pdf

Kunio Kashino, Yasunori Ohishi, Daiki Takeuchi, 2020, DCASE.

LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

H. Zen, M. Bacchiani, Ankur Bapna, 2023, INTERSPEECH.

SNRi Target Training for Joint Speech Enhancement and Recognition

M. Bacchiani, A. Narayanan, Yuma Koizumi, 2021, INTERSPEECH.

Stable Training of Dnn for Speech Enhancement Based on Perceptually-Motivated Black-Box Cost Function

Kohei Yatabe, Ryoichi Miyazaki, Yuma Koizumi, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised Detection of Anomalous Sound Based on Deep Learning and the Neyman–Pearson Lemma

Yuma Koizumi, Shoichiro Saito, Noboru Harada, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Invertible DNN-Based Nonlinear Time-Frequency Transform for Speech Enhancement

K. Yatabe, Yasuhiro Oikawa, Daiki Takeuchi, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Griffin–Lim Iteration

Yasuhiro Oikawa, Noboru Harada, Yuma Koizumi, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Real-Time Speech Enhancement Using Equilibriated RNN

Yasuhiro Oikawa, Daiki Takeuchi, Kohei Yatabe, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Optimizing acoustic feature extractor for anomalous sound detection based on Neyman-Pearson lemma

Noboru Harada, Yuma Koizumi, Shoichiro Saito, 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

Supervised source enhancement composed of nonnegative auto-encoders and complementarity subtraction

Yusuke Hioka, Kazunori Kobayashi, Kenta Niwa, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SPIDERnet: Attention Network For One-Shot Anomaly Detection In Sounds

Masahiro Yasuda, Shoichiro Saito, Noboru Harada, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Two-class Hyper-spherical Autoencoder for Supervised Anomaly Detection

Noboru Harada, Yuma Koizumi, Yuta Kawachi, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

H. Zen, M. Bacchiani, Ankur Bapna, 2023, 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Deep Griffin–Lim Iteration: Trainable Iterative Phase Reconstruction Using Neural Network

Yasuhiro Oikawa, Yoshiki Masuyama, Kohei Yatabe, 2021, IEEE Journal of Selected Topics in Signal Processing.

Proceedings of Meetings on Acoustics

K. Itou, Yuma Koizumi, 2012 .

Description and Discussion on DCASE 2023 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Tomoya Nishida, Kota Dohi, Takashi Endo, 2023, ArXiv.

Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques

Tomoya Nishida, Kota Dohi, Takashi Endo, 2022, DCASE.

AdaFlow: Domain-adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-domain Translation

Noboru Harada, Yuma Koizumi, Masataka Yamaguchi, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Mask Scalars for Improved Robust Automatic Speech Recognition

A. Narayanan, N. Howard, Yuma Koizumi, 2023, 2022 IEEE Spoken Language Technology Workshop (SLT).

Mask scalar prediction for improving robust automatic speech recognition

A. Narayanan, N. Howard, Yuma Koizumi, 2022, ArXiv.

Anomaly Detection Technique in Sound to Detect Faulty Equipment

N. Harada, Yuma Koizumi, Hisashi Uematsu, 2017, NTT Technical Review.

DOA Estimation by DNN-based Denoising and Dereverberation from Sound Intensity Vector pdf

Masahiro Yasuda, Shoichiro Saito, Hisashi Uematsu, 2019, ArXiv.