Related papers: TeCANet: Temporal-Contextual Attention Network for…
Speech dereverberation in distant-microphone scenarios remains challenging due to the high correlation between reverberation and target signals, often leading to poor generalization in real-world environments. We propose IF-CorrNet, a…
We propose a novel Neural Steering technique that adapts the target area of a spatial-aware multi-microphone sound source separation algorithm during inference without the necessity of retraining the deep neural network (DNN). To achieve…
Deep neural networks (DNNs) are very effective for multichannel speech enhancement with fixed array geometries. However, it is not trivial to use DNNs for ad-hoc arrays with unknown order and placement of microphones. We propose a novel…
In this study, we propose a dense frequency-time attentive network (DeFT-AN) for multichannel speech enhancement. DeFT-AN is a mask estimation network that predicts a complex spectral masking pattern for suppressing the noise and…
The widespread adoption of artificial intelligence (AI) in next-generation communication systems is challenged by the heterogeneity of traffic and network conditions, which call for the use of highly contextual, site-specific, data. A…
Anomalous audio in speech recordings is often caused by speaker voice distortion, external noise, or even electric interferences. These obstacles have become a serious problem in some fields, such as high-quality music mixing and speech…
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for…
With the rapid development of Natural Language Processing (NLP) technologies, text steganography methods have been significantly innovated recently, which poses a great threat to cybersecurity. In this paper, we propose a novel attentional…
Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification.…
Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited…
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…
We propose a speech enhancement method using a causal deep neural network~(DNN) for real-time applications. DNN has been widely used for estimating a time-frequency~(T-F) mask which enhances a speech signal. One popular DNN structure for…
A major advantage of a deep convolutional neural network (CNN) is that the focused receptive field size is increased by stacking multiple convolutional layers. Accordingly, the model can explore the long-range dependency of features from…
We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…
Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of…
In recent years, Deep Learning has been successfully applied to multimodal learning problems, with the aim of learning useful joint representations in data fusion applications. When the available modalities consist of time series data such…
In recent years, significant progress has been made in the medical image analysis domain using convolutional neural networks (CNNs). In particular, deep neural networks based on a U-shaped architecture (UNet) with skip connections have been…
Speech enhancement (SE) improves communication in noisy environments, affecting areas such as automatic speech recognition, hearing aids, and telecommunications. With these domains typically being power-constrained and event-based while…
Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…
In recent years, speech enhancement (SE) has achieved impressive progress with the success of deep neural networks (DNNs). However, the DNN approach usually fails to generalize well to unseen environmental noise that is not included in the…