Naoki Murata

Naoki Murata

Auto-generated profile, based on publicly available information

Naoki Murata

Sony AI

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 August 2024
Verified
Conference Paper
Open access
PDF file
YZYixiao Zhang
Yixiao Zhang
YIYukara Ikemiya
Yukara Ikemiya
GXGus Xia
Gus Xia
NMNaoki Murata
Naoki Murata
MMMarco A. Martínez-Ramírez
Marco A. Martínez-Ramírez
SDSimon Dixon
Simon Dixon
Recent advances in text-to-music generation models have opened new avenues in musical creativity. However, the task of editing these generated music remains a significant challenge. This paper introduces a novel approach to edit music generated by such models, enabling the modification of specific attributes, such as genre, mood, and instrument, while maintaining other aspects unchanged. Our method transforms text editing to the latent space manipulation, and adds an additional constraint to enforce consistency. It seamlessly integrates with existing pretrained text-to-music diffusion models without requiring additional training. Experimental results demonstrate superior performance over both zero-shot and certain supervised baselines in style and timbre transfer evaluations. We also show the practical applicability of our approach in real-world music editing scenarios.

20 August 2023
Verified
Conference Paper
Open access
RSRyosuke Sawata
Ryosuke Sawata
NMNaoki Murata
Naoki Murata
YTYuhta Takida
Yuhta Takida
TUToshimitsu Uesaka
Toshimitsu Uesaka
TSTakashi Shibuya
Takashi Shibuya
YMYuki Mitsufuji
Yuki Mitsufuji

27 December 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
YMYu Maeno
Yu Maeno
YMYuki Mitsufuji
Yuki Mitsufuji
PSPrasanga Samarasinghe
Prasanga Samarasinghe
NMNaoki Murata
Naoki Murata
TAThushara D. Abhayapala
Thushara D. Abhayapala
Active acoustic noise attenuation over a sizable space is a challenging problem in acoustic signal processing. The noise attenuation performance of feedforward active noise control (ANC) relies on the preciseness of a reference signal of a primary noise field. To capture the precise reference signal for controlling a sizable space, a large number of reference microphones are required, which reduces system viability. In this study, we exploit an efficient representation of the reference signal in spherical harmonic (SH) domain by utilizing the inherent sparseness of the noise field. The main contributions of this work are as follows. (1) A general reference microphone geometry can be used. The implementation difficulty in the array structure, which is recognized as the common issue of mode-domain signal processing, e.g., use of a fully surrounding spherical array, is reduced by using the mode translation theorem. (2) The accuracy of low-frequency signal decomposition is improved. The low accuracy of low-frequency signal decomposition in compressive sensing (CS), which is commonly reported in the literature, is improved by applying mode-domain signal representation. (3) System robustness is increased. The robustness of the system is increased by considering a noise source spatial distribution of both the interior and exterior sound fields, which is not possible in the case of a straightforward general mode-domain signal representation. Experimental results indicate that the noise attenuation performance of our proposed method exceeds that of existing solutions. The fiexibility of the array structure is also increased, which leads to a more feasible practical system setup.

1 March 2016
Verified
Conference Paper
Closed access
NMNaoki Murata
Naoki Murata
SKShoichi Koyama
Shoichi Koyama
HKHirokazu Kameoka
Hirokazu Kameoka
NTNorihiro Takamune
Norihiro Takamune
HSHiroshi Saruwatari
Hiroshi Saruwatari
A sparse sound field decomposition method using prior information on source signals in the time-frequency domain is proposed. Sparse sound field decomposition has been proved to be effective for various acoustic signal processing applications. Current methods for sparse decomposition are based only on the spatial sparsity of the source distribution. However, it can be assumed that possible source signals to be decomposed are approximately known in advance. To exploit this prior information, we incorporated the complex nonnegative factorization model into sparse sound field decomposition. Since the magnitude spectrum of the possible source signals can be trained in advance, accuracy of the sparse decomposition can be improved even when the source signals are highly correlated and the sources are in a highly noisy environment. In addition, the proposed decomposition algorithm is derived using the auxiliary function method. Numerical experiments indicated that the sparse decomposition performance was significantly improved using the proposed method.

1 January 2016 in Procedia Engineering
Verified
Journal Article
Open access
RIR. Imamura
R. Imamura
TSToshinori Shimanouchi
Toshinori Shimanouchi
NMN. Murata
N. Murata
KYK. Yamashita
K. Yamashita
MFMasayuki Fukuzawa
Masayuki Fukuzawa
MNMinoru Noda
Minoru Noda

28 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
YHYutong He
Yutong He
NMNaoki Murata
Naoki Murata
CLChieh-Hsin Lai
Chieh-Hsin Lai
YTYuhta Takida
Yuhta Takida
TUToshimitsu Uesaka
Toshimitsu Uesaka
SEStefano Ermon
Stefano Ermon
Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework that leverages pretrained diffusion models and off-the-shelf neural networks with minimal additional inference cost for a broad range of tasks. Specifically, we leverage the manifold hypothesis to refine the guided diffusion steps and introduce a shortcut algorithm in the process. We then propose two methods for on-manifold training-free guidance using pre-trained autoencoders and demonstrate that our shortcut inherently preserves the manifolds when applied to latent diffusion models. Our experiments show that MPGD is efficient and effective for solving a variety of conditional generation applications in low-compute settings, and can consistently offer up to 3.8x speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.