Výsledky vyhledávání - "Kouhei Sekiguchi"

Neural Full-Rank Spatial Covariance Analysis for Blind Source Separation

Autor: Kouhei Sekiguchi, Aditya Arie Nugraha, Kazuyoshi Yoshii, Yoshiaki Bando, Yoshiki Masuyama, Mathieu Fontaine

Publikováno v: IEEE Signal Processing Letters. 28:1670-1674

This paper describes aneural blind source separation (BSS) method based on amortized variational inference (AVI) of a non-linear generative model of mixture signals. A classical statistical approach to BSS is to fit a linear generative model that con

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::768eda411a3234efb74d93d3642a497c
https://doi.org/10.1109/lsp.2021.3101699

Zobrazit plný text záznamu

Fast Multichannel Nonnegative Matrix Factorization With Directivity-Aware Jointly-Diagonalizable Spatial Covariance Matrices for Blind Source Separation

Autor: Tatsuya Kawahara, Kazuyoshi Yoshii, Aditya Arie Nugraha, Kouhei Sekiguchi, Yoshiaki Bando

Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:2610-2625

This article describes a computationally-efficient blind source separation (BSS) method based on the independence, low-rankness, and directivity of the sources. A typical approach to BSS is unsupervised learning of a probabilistic model that consists

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::adf49157c0ad54bf9f9effc37f01f458
https://doi.org/10.1109/taslp.2020.3019181

Zobrazit plný text záznamu

Flow-Based Independent Vector Analysis for Blind Source Separation

Autor: Aditya Arie Nugraha, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii, Kouhei Sekiguchi

Publikováno v: IEEE Signal Processing Letters. 27:2173-2177

This letter describes a time-varying extension of independent vector analysis (IVA) based on the normalizing flow (NF), called NF-IVA, for determined blind source separation of multichannel audio signals. As in IVA, NF-IVA estimates demixing matrices

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a370e9dec83c598151f685101551c175
https://doi.org/10.1109/lsp.2020.3039944

Zobrazit plný text záznamu

Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation

Autor: Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii

Publikováno v: HAL

This paper describes a blind source separation method for multichannel audio signals, called NF-FastMNMF, based on the integration of the normalizing flow (NF) into the multichannel nonnegative matrix factorization with jointly-diagonalizable spatial

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00189bbdfb3e05f7a150ae17c2060fa7
https://hal.telecom-paris.fr/hal-03637425

Zobrazit plný text záznamu

Semi-Supervised Multichannel Speech Enhancement With a Deep Speech Prior

Autor: Kouhei Sekiguchi, Tatsuya Kawahara, Yoshiaki Bando, Aditya Arie Nugraha, Kazuyoshi Yoshii

Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27:2197-2212

This paper describes a semi-supervised multichannel speech enhancement method that uses clean speech data for prior training. Although multichannel nonnegative matrix factorization (MNMF) and its constrained variant called independent low-rank matrix

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::11300e31280b7b701976ad4f39352c36
https://doi.org/10.1109/taslp.2019.2944348

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání