• Publications
  • Influence
Logic synthesis for look-up table based FPGAs using functional decomposition and support minimization
TLDR
This paper presents a logic synthesis method for look-up table (LUT) based field programmable gate arrays (FPGAs) by functional decomposition and Boolean resubstitution. Expand
  • 46
  • 2
BLIND SPARSE SOURCE SEPARATION WITH SPATIALLY SMOOTHED TIME-FREQUENCY MASKING 1
In this paper, we handle the blind sparse source separation problem with time-frequency masks. Some existing methods employ time-frequency binary masks to extract the signals, and therefore, theExpand
  • 26
  • 2
  • PDF
A review of blind source separation methods: two converging routes to ILRMA originating from ICA and NMF
TLDR
This paper describes several important methods for the blind source separation of audio signals in an integrated manner. Expand
  • 19
  • 1
  • PDF
A Causal Frequency-Domain Implementation of a Natural Gradient Multichannel Blind Deconvolution and Source Separation Algorithm
Natural gradient adaptation is useful for developing block-based adaptive solutions to convolutive blind source separation tasks, in which frequency-domain fast convolution methods can be exploitedExpand
  • 3
  • 1
  • PDF
Automatic pursuit routing for mobile communications network
TLDR
This paper describes an automatic pursuit routing capability necessary for a public land mobile network because mobile stations move freely through service areas. Expand
  • 2
An Efficient Method for Generating Kernels on Implicit Cube Set Representations
In the process of logic synthesis and optimization, it is an important operation to extract common logic parts among several logic functions. Most methods currently used are based on SOPExpand
  • 5
  • PDF
General Formulation of Multichannel Extensions of NMF Variants
TLDR
This chapter provides a general formulation of the frequency domain BSS that makes it possible to incorporate the models for the source power spectrogram and the source spatial covariance matrix. Expand
  • 4
Underdetermined Blind Separation of Convolutive Mixtures of Speech by Combining Time-frequency Masks and ICA
We propose a method for separating speech signals when sources outnumber sensors. Several methods have already been proposed for solving the underdetermined blind separation problem for convolutiveExpand
  • 2
  • PDF
Similarity Search-based Blind Source Separation
  • H. Sawada, K. Aoyama
  • Computer Science
  • ICASSP - IEEE International Conference on…
  • 10 May 2019
TLDR
We propose a new method for blind source separation, where we perform similarity search for a prepared clean speech database and update the LGM variance parameters by using the similarity search results. Expand
  • 1
  • PDF