Yoshiaki Bando

DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF

Jul 22, 2022
Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii

Figure 2 for DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF

Figure 3 for DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF

Figure 4 for DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF

* IWAENC 2022

Access Paper or Ask Questions

Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

Jul 15, 2022
Kouhei Sekiguchi, Aditya Arie Nugraha, Yicheng Du, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii

Figure 1 for Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

Figure 2 for Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

Figure 3 for Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

Figure 4 for Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments

* IEEE/RSJ IROS 2022

Access Paper or Ask Questions

Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments

Jul 15, 2022
Yicheng Du, Aditya Arie Nugraha, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii

Figure 2 for Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments

* INTERSPEECH 2022

Access Paper or Ask Questions

Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

May 11, 2022
Mathieu Fontaine, Kouhei Sekiguchi, Aditya Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii

Figure 2 for Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

Figure 3 for Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

Figure 4 for Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

* IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2022, pp.1-1

Access Paper or Ask Questions

Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling

Jul 28, 2020
Yoshiki Masuyama, Yoshiaki Bando, Kohei Yatabe, Yoko Sasaki, Masaki Onishi, Yasuhiro Oikawa

Figure 2 for Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling

Figure 3 for Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling

Figure 4 for Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling

* Accepted for publication in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Access Paper or Ask Questions

Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model

Aug 29, 2019
Yoshiaki Bando, Yoko Sasaki, Kazuyoshi Yoshii

Figure 2 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model

Figure 3 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model

Figure 4 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model

* 6 pages, 2 figures, accepted for publication in 2019 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

Access Paper or Ask Questions

Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition

Mar 31, 2019
Kazuki Shimada, Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

Figure 2 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition

Figure 3 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition

Figure 4 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition

Access Paper or Ask Questions

Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices

Mar 08, 2019
Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii

Figure 2 for Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices

Access Paper or Ask Questions

Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Mar 19, 2018
Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

Figure 1 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Figure 2 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Figure 3 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Figure 4 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

* 5 pages, 3 figures, version that Eqs. (9), (19), and (20) in v2 (submitted to ICASSP 2018) are corrected. Samples available here: http://sap.ist.i.kyoto-u.ac.jp/members/yoshiaki/demo/vae-nmf/

Access Paper or Ask Questions