An overview of machine learning and other data-based methods for spatial audio capture, processing, and reproduction

M Cobos, J Ahrens, K Kowalczyk, A Politis - EURASIP Journal on Audio …, 2022 - Springer
The domain of spatial audio comprises methods for capturing, processing, and reproducing
audio content that contains spatial information. Data-based methods are those that operate …

Ensemble of ACCDOA-and EINV2-based systems with D3Nets and impulse response simulation for sound event localization and detection

K Shimada, N Takahashi, Y Koyama… - arxiv preprint arxiv …, 2021 - arxiv.org
This report describes our systems submitted to the DCASE2021 challenge task 3: sound
event localization and detection (SELD) with directional interference. Our previous system …

Acoustic source localization in the spherical harmonics domain exploiting low-rank approximations

M Cobos, M Pezzoli, F Antonacci… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Acoustic signal processing in the spherical harmonics domain (SHD) is an active research
area that exploits the signals acquired by higher order microphone arrays. A very important …

[HTML][HTML] Spherical-harmonics-based sound field decomposition and multichannel nmf for sound source separation

M Pezzoli, J Carabias-Orti, P Vera-Candeas… - Applied Acoustics, 2024 - Elsevier
In the context of source separation solutions for virtual reality applications, several
techniques in the spherical harmonics domain have been proposed in the literature. The …

Spatial data augmentation with simulated room impulse responses for sound event localization and detection

Y Koyama, K Shigemi, M Takahashi… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Recording and annotating real sound events for a sound event localization and detection
(SELD) task is time consuming, and data augmentation techniques are often favored when …

Semi-blind source separation using convolutive transfer function for nonlinear acoustic echo cancellation

G Cheng, L Liao, K Chen, Y Hu, C Zhu… - The Journal of the …, 2023 - pubs.aip.org
The recently proposed semi-blind source separation (SBSS) method for nonlinear acoustic
echo cancellation (NAEC) outperforms adaptive NAEC in attenuating the nonlinear acoustic …

Direction specific ambisonics source separation with end-to-end deep learning

F Lluís, N Meyer-Kahlen… - Acta …, 2023 - acta-acustica.edpsciences.org
Ambisonics is a scene-based spatial audio format that has several useful features compared
to object-based formats, such as efficient whole scene rotation and versatility. However, it …

A physics-informed neural network-based approach for the spatial upsampling of spherical microphone arrays

F Miotello, F Terminiello, M Pezzoli… - … on Acoustic Signal …, 2024 - ieeexplore.ieee.org
Spherical microphone arrays are convenient tools for capturing the spatial characteristics of
a sound field. However, achieving superior spatial resolution requires arrays with numerous …

面向卷积混叠环境下的盲源分离新方法

解元, 邹涛, 孙为军, 谢胜利 - 自动化学报, 2023 - aas.net.cn
卷积混叠环境下的盲源分离(Blind source separation, BSS) 是一个极具挑战性和实际意义的
问题. 本文在独立分量分析框架下, 建立非负矩阵分解(Nonnegative matrix factorization, NMF) …

Efficient FPGA implementation for sound source separation using direction-informed multichannel non-negative matrix factorization

P Diel, AJ Muñoz-Montoro, JJ Carabias-Orti… - The Journal of …, 2024 - Springer
Sound source separation (SSS) is a fundamental problem in audio signal processing,
aiming to recover individual audio sources from a given mixture. A promising approach is …