Related papers: Enhancing Stereo Sound Event Detection with BiMamb…

While recent semantic segmentation networks heavily rely on powerful pretrained encoders, most employ simplistic decoders, leading to suboptimal trade-offs between semantic context and fine-grained detail preservation. To address this, we…

Although the complex spectrum-based speech enhancement(SE) methods have achieved significant performance, coupling amplitude and phase can lead to a compensation effect, where amplitude information is sacrificed to compensate for the phase…

Localizing sounds and detecting events in different room environments is a difficult task, mainly due to the wide range of reflections and reverberations. When training neural network models with sounds recorded in only a few room…

In this report, we propose three novel methods for developing a sound event detection (SED) model for the DCASE 2024 Challenge Task 4. First, we propose an auxiliary decoder attached to the final convolutional block to improve feature…

Deep learning-based Sound Event Localization and Detection (SELD) systems degrade significantly on real-world, long-tailed datasets. Standard regression losses bias learning toward frequent classes, causing rare events to be systematically…

This paper presents a new learning strategy for the Sound Event Detection (SED) system to tackle the issues of i) knowledge migration from a pre-trained model to a new target model and ii) learning new sound events without forgetting the…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

The Transformer model, particularly its cross-attention module, is widely used for feature fusion in target sound extraction which extracts the signal of interest based on given clues. Despite its effectiveness, this approach suffers from…

Sound event detection (SED) and localization refer to recognizing sound events and estimating their spatial and temporal locations. Using neural networks has become the prevailing method for SED. In the area of sound localization, which is…

Quad Bayer demosaicing is the central challenge for enabling the widespread application of Hybrid Event-based Vision Sensors (HybridEVS). Although existing learning-based methods that leverage long-range dependency modeling have achieved…

Meta-learning facilitates few-shot hyperspectral target detection (HTD), but adapting deep backbones remains challenging. Full-parameter fine-tuning is inefficient and prone to overfitting, and existing methods largely ignore the…

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential…

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

Convolutional neural networks have primarily led 3D medical image segmentation but may be limited by small receptive fields. Transformer models excel in capturing global relationships through self-attention but are challenged by high…

While multitask and transfer learning has shown to improve the performance of neural networks in limited data settings, they require pretraining of the model on large datasets beforehand. In this paper, we focus on improving the performance…

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…

Joint sound event localization and detection (SELD) is an integral part of developing context awareness into communication interfaces of mobile robots, smartphones, and home assistants. For example, an automatic audio focus for video…

Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called…

Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue…

Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing…