K. Kobayashi

This paper proposes a multiple satellite MIMO receiver that can handle the large spatial correlation and the different propagation delay of paths created by the use of multiple satellites. Expand

A method for separating underdetermined sound sources based on a novel power spectral density (PSD) estimation is proposed that enables up to M(M-1)+1 sources to be separated when we use a microphone array of M sensors and a Wiener post-filter calculated by the estimated PSDs. Expand

We propose a training method for deep neural network (DNN) based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation of speech quality. Expand

We investigated whether a deep neural network (DNN)-based source enhancement function can be self-optimized by reinforcement learning (RL). Expand

A microphone array post-filter design effective in various noise environments is proposed for implementation in a hands-free speech interface. Expand

We propose an alternative approach to this estimation process that uses a neural network to implement the approximation by using a non-linear function. Expand

We propose requirements for the de-mixing matrix using the property of the M-matrix. Expand

An acoustic echo cancellation (AEC) method developed for voice over IP (VoIP) hands-free applications is proposed. Expand