Polyphonic sound event localization and detection based on Multiple Attention Fusion ResNet.

Sound event localization and detection have been applied in various fields. Due to the polyphony and noise interference, it becomes challenging to accurately predict the sound event and their occurrence locations. Aiming at this problem, we propose a Multiple Attention Fusion ResNet, which uses ResNet34 as the base network. Given the situation that the sound duration is not fixed, and there are multiple polyphonic and noise, we introduce the Gated Channel Transform to enhance the residual basic block. This enables the model to capture contextual information, evaluate channel weights, and reduce the interference caused by polyphony and noise. Furthermore, Split Attention is introduced to the model for capturing cross-channel information, which enhances the ability to distinguish the polyphony. Finally, Coordinate Attention is introduced to the model so that the model can focus on both the channel information and spatial location information of sound events. Experiments were conducted on two different datasets, TAU-NIGENS Spatial Sound Events 2020, and TAU-NIGENS Spatial Sound Events 2021. The results demonstrate that the proposed model significantly outperforms state-of-the-art methods under multiple polyphonic and noise-directional interference environments and it achieves competitive performance under a single polyphonic environment.

Mac Protein is not an Essential Virulence Factor for the Virulent Reference Strain Streptococcus suis P1/7.

Streptococcus suis is a major pathogen of pigs and also an important zoonotic agent for humans. A S. suis protein containing Mac-1 domain (designated Mac) is a protective antigen, exclusively cleaves porcine IgM, and contributes to complement evasion with the presence of high titers of specific porcine anti-S. suis IgM, but its role in S. suis virulence has not been investigated in natural healthy host without specific IgM. In this study, a mac deletion mutant was constructed by homologous recombination in S. suis serotype 2 virulent reference strain P1/7. Deletion of mac did not significantly influence phagocytosis or intracellular survival within murine macrophages RAW264.7, or the oxidative-burst induction of RAW264.7 and murine neutrophils. Furthermore, the mutant is as virulent as the wild-type strain in pig, mouse, and zebrafish infection models. Our data suggest that Mac is not essential for S. suis virulence in strain P1/7 in natural healthy host without specific IgM, and the immunogenicity of Mac does not appear to correlate with its significance for virulence.