Seisuke Kyochi

Seisuke Kyochi

Auto-generated profile, based on publicly available information

Seisuke Kyochi

Kogakuin University, Tokyo, Japan

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2017 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Open access
RMRyo Matsuoka
Ryo Matsuoka
SKSeisuke Kyochi
Seisuke Kyochi
SOShunsuke Ono
Shunsuke Ono
MOMasahiro Okuda
Masahiro Okuda
This paper proposes a new optimization framework for the joint optimization of sparsity and filter order (JOSFO) for FIR filter design. Since the cost function for JOSFO involves ℓ 0 and non-uniform overlapped group ℓ 0 norms, which are not convex, a global optimal solution is difficult to obtain. To find an approximate solution of the non-convex problem, existing approaches repeat the following steps: 1) approximate the cost function; 2) find candidates of zero coefficients by minimizing the cost function; and 3) set them to zero. On the other hand, this paper directly solves the optimization problem, without any approximation to the cost function, by using the alternating direction method of multipliers with the pseudo-proximity operators of ℓ 0 and non-uniform non-overlapped group ℓ 0 norms. Experimental results show that resulting filters designed by the proposed method have sparser coefficients and lower orders, while satisfying filter specifications, such as an error from a desired frequency response.

1 April 2018
Verified
Conference Paper
Closed access
KSKenjiro Sugimoto
Kenjiro Sugimoto
SKSeisuke Kyochi
Seisuke Kyochi
SKSei-Ichiro Kamata
Sei-Ichiro Kamata
This paper presents a universal approach for constant-time Gaussian filters (O(1) GF) based on the Discrete Cosine Transform (DCT). It is well known that DCT has the eight types of definitions. Existing methods of O(1) GF use difference DCT type according to their original concepts. However, all types of DCT have not been studied comprehensively and quantitatively. Unlike existing methods, the proposed approach covers all types of DCT and moment preservation for arbitrary orders, which enables us to clarify differences of O(1) GF derived from each DCT through a comprehensive analysis. Based on the universal approach, a closed-form solution to optimize weight coefficients is also proposed based on a simple convex analysis. Experiments found that DCT-7 shows the highest approximate accuracy, which is a new conclusion different from existing methods.

3 February 2021 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
SKSeisuke Kyochi
Seisuke Kyochi
SOShunsuke Ono
Shunsuke Ono
ISIvan Selesnick
Ivan Selesnick
This paper proposes an epigraphical relaxation (ERx) technique for non-proximable mixed norm minimization. Mixed norm regularization methods play a central role in signal reconstruction and processing, where their optimization relies on the fact that the proximity operators of the mixed norms can be computed efficiently. To bring out the power of regularization, sophisticated layered modeling of mixed norms that can capture inherent signal structure is a key ingredient, but the proximity operator of such a mixed norm is often unavailable (non-proximable). Our ERx decouples a layered non-proximable mixed norm into a norm and multiple epigraphical constraints. This enables us to handle a wide range of non-proximable mixed norms in optimization, as long as both the proximal operator of the outermost norm and the projection onto each epigraphical constraint are efficiently computable. Moreover, under mild conditions, we prove that ERx does not change the minimizer of the original problem despite relaxing equality constraints into inequality ones. We also develop new regularizers based on ERx:one is decorrelated structure-tensor total variation for color image restoration, and the other is amplitude-spectrum nuclear norm for low-rank amplitude recovery. We examine the power of these regularizers through experiments, which illustrates the utility of ERx.

1 May 2019
Verified
Conference Paper
Open access
KIKeisuke Imoto
Keisuke Imoto
SKSeisuke Kyochi
Seisuke Kyochi
The types of sound events that occur in a situation are limited, and some sound events are likely to co-occur; for instance, "dishes" and "glass jingling." In this paper, we propose a technique of sound event detection utilizing graph Laplacian regularization taking the sound event co-occurrence into account. In the proposed method, sound event occurrences are represented as a graph whose nodes indicate the frequency of event occurrence and whose edges indicate the co-occurrence of sound events. This graph representation is then utilized for sound event modeling, which is optimized under an objective function with a regularization term considering the graph structure. Experimental results obtained using TUT Sound Events 2016 development, 2017 development, and TUT Acoustic Scenes 2016 development indicate that the proposed method improves the detection performance of sound events by 7.9 percentage points compared to that of the conventional CNN-BiGRU-based method in terms of the segment-based F1-score. Moreover, the results show that the proposed method can detect co-occurring sound events more accurately than the conventional method.

23 May 2014 in IEEE Transactions on Signal Processing
Verified
Journal Article
Open access
SKSeisuke Kyochi
Seisuke Kyochi
YTYuichi Tanaka
Yuichi Tanaka
Complex-valued conjugate-symmetric Hadamard transforms (C-CSHT) are variants of complex Hadamard transforms and found applications in signal processing. In addition, their real-valued transform counterparts (R-CSHTs) perform comparably with Hadamard transforms (HTs) despite their lower computational complexity. Closed-form factorizations of C-CSHTs and R-CSHTs have recently been proposed to make calculations more efficient. However, there is still room to find effective and general factorizations. This paper presents a simple closed-form complete factorization of C-CSHTs based on that of R-CSHTs. The proposed factorization can be applied to both C- and R-CSHTs with one factorization and it provides several benefits: 1) It can save total implementation costs for both C-CSHTs and R-CSHTs; 2) the generalized R-CSHT factorization significantly reduces its computational cost; 3) memory-saved local orientation detection of images can be achieved; 4) a fast direction-aware transform can be attained; 5) it clarifies that C- and R-CSHTs are closely related to common block transforms, such as the discrete Fourier transform (DFT), binDCT, and HT; and 6) it achieves a new integer complex-valued transform, which can approximate the DFT better than the original C-CSHT. The image orientation estimation and performance in image coding of our R-CSHTs were evaluated through examples of practical applications based on the proposed factorization.

9 November 2017 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
RIRyoma Ishibashi
Ryoma Ishibashi
TSTaizo Suzuki
Taizo Suzuki
SKSeisuke Kyochi
Seisuke Kyochi
HKHiroyuki Kudo
Hiroyuki Kudo
We present a novel image boundary extension, mean value extension (MVE), for directional lapped transforms, particularly cosine-sine modulated lapped transforms (CSMLTs). Lapped transforms are usually used with an extension technique, such as periodic extension (PE) or symmetric extension (SE), for nonexpansive convolution at signal boundaries. When directional textures (oblique lines and curves) appear at the 2D signal (image) boundaries, both PE and SE produce directional discontinuities, which degrade the sparsity of the transformed coefficients, especially in the case of directional lapped transforms. MVE reduces the discontinuities for directional textures better than PE or SE do; it thus improves the efficiency of the sparse representation based on directional lapped transforms. Moreover, to reduce computational costs compared with those of directional lapped transforms, we introduce new directional block transforms, called cosine-sine modulated block transforms (CSMBTs). These new transforms are derived from a minimum tile processing (tiling) of M-band CSMLTs with 2M filter lengths and nonexpansive convolutions. The resulting directional block transforms, particularly in the case of the MVE, have richer directional selectivity and have higher performance compared with a discrete Fourier transform (DFT) as shown in experiments.