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

This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build…

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

Kernel methods play a critical role in many machine learning algorithms. They are useful in manifold learning, classification, clustering and other data analysis tasks. Setting the kernel's scale parameter, also referred to as the kernel's…

This paper presents a simple but effective method that uses multi-resolution feature maps with convolutional neural networks (CNNs) for anti-spoofing in automatic speaker verification (ASV). The central idea is to alleviate the problem that…

In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding…

The transcriptomics of cancer tumors are characterized with tens of thousands of gene expression features. Patient prognosis or tumor stage can be assessed by machine learning techniques like supervised classification tasks given a gene…

We propose a speaker selection mechanism (SSM) for the training of an end-to-end beamforming neural network, based on recent findings that a listener usually looks to the target speaker with a certain undershot angle. The mechanism allows…

This paper describes the architecture and performance of ORACLE, an approach for detecting a unique radio from a large pool of bit-similar devices (same hardware, protocol, physical address, MAC ID) using only IQ samples at the physical…

A major goal in blind source separation to identify and separate sources is to model their inherent characteristics. While most state-of-the-art approaches are supervised methods trained on large datasets, interest in non-data-driven…

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet…

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…

Transformer-based models have become the state of the art across multiple domains, from natural language processing to machine listening, thanks to the attention mechanisms. However, the attention layers require a large number of parameters…

Phase-based features related to vocal source characteristics can be incorporated into magnitude-based speaker recognition systems to improve the system performance. However, traditional feature-level fusion methods typically ignore the…

We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture…

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant…

How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information…

Deep convolutional neural networks (DCNNs) have substantially advanced object detection capabilities, particularly in remote sensing imagery. However, challenges persist, especially in detecting small objects where the high resolution of…

We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel function (exponential power kernel) with a highly efficient…

It has been proven that, compared to using 32-bit floating-point numbers in the training phase, Deep Convolutional Neural Networks (DCNNs) can operate with low precision during inference, thereby saving memory space and power consumption.…