相关论文: Frequency and Multi-Scale Selective Kernel Attenti…

With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging…

In this paper, Whisper, a large-scale pre-trained model for automatic speech recognition, is proposed to apply to speaker verification. A partial multi-scale feature aggregation (PMFA) approach is proposed based on a subset of Whisper…

Kernel method is a very powerful tool in machine learning. The trick of kernel has been effectively and extensively applied in many areas of machine learning, such as support vector machine (SVM) and kernel principal component analysis…

Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…

Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such…

In this paper, we proposed large selective kernel and sparse attention network (LSKSANet) for remote sensing image semantic segmentation. The LSKSANet is a lightweight network that effectively combines convolution with sparse attention…

Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the…

Scaling language models to handle longer input sequences typically necessitates large key-value (KV) caches, resulting in substantial memory overhead during inference. In this paper, we propose Tensor Product Attention (TPA), a novel…

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is…

Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time…

Spiking Neural Networks (SNNs) can offer ultra-low power/energy consumption for machine learning-based application tasks due to their sparse spike-based operations. Currently, most of the SNN architectures need a significantly larger model…

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using…

Semantic matching is of central significance to the answer selection task which aims to select correct answers for a given question from a candidate answer pool. A useful method is to employ neural networks with attention to generate…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities…

Convolutions have become essential in state-of-the-art end-to-end Automatic Speech Recognition~(ASR) systems due to their efficient modelling of local context. Notably, its use in Conformers has led to superior performance compared to…

In this study we present a kernel based convolution model to characterize neural responses to natural sounds by decoding their time-varying acoustic features. The model allows to decode natural sounds from high-dimensional neural…