Related papers: An efficient encoder-decoder architecture with top…

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have…

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the…

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

The encoder-decoder architecture is widely used as a lightweight semantic segmentation network. However, it struggles with a limited performance compared to a well-designed Dilated-FCN model for two major problems. First, commonly used…

Although the capacity of deep generative models for image generation, such as Diffusion Models (DMs) and Generative Adversarial Networks (GANs), has dramatically improved in recent years, much of their success can be attributed to…

Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of…

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural…

The quadratic complexity of dot-product attention introduced in Transformer remains a fundamental bottleneck impeding the progress of foundation models toward unbounded context lengths. Addressing this challenge, we introduce the Deep…

Low-dose computed tomography (LDCT) and positron emission tomography (PET) have emerged as safer alternatives to conventional imaging modalities by significantly reducing radiation exposure. However, current approaches often face a…

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily…

In recent years, deep learning (DL) models have shown outstanding performance in EEG classification tasks, particularly in Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer-Interfaces(BCI)systems. DL methods have been…

This paper presents a novel design of attention model for text-independent speaker verification. The model takes a pair of input utterances and generates an utterance-level embedding to represent speaker-specific characteristics in each…

Transformer-based architectures for speaker verification typically require more training data than ECAPA-TDNN. Therefore, recent work has generally been trained on VoxCeleb1&2. We propose a backbone network based on self-attention, which…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

The human auditory system has the ability to selectively focus on key speech elements in an audio stream while giving secondary attention to less relevant areas such as noise or distortion within the background, dynamically adjusting its…