Speech Enhancement is significantly applied in speech processing, as a foundation for downstream tasks. Nowadays, neural networks are well applied in speech enhancement. However, there remain considerable difficulties...
详细信息
ISBN:
(纸本)9789819755905;9789819755912
Speech Enhancement is significantly applied in speech processing, as a foundation for downstream tasks. Nowadays, neural networks are well applied in speech enhancement. However, there remain considerable difficulties for neural networks to improve speech quality. Firstly, existing methods have the problem of speech over-suppression. Because they have not yet taken into account that neural networks influence not only background noise but also clean speech during enhancement. This issue can negatively impact the following tasks. Secondly, striking a balance between model complexity and performance is crucial, especially when deploying on resource-constrained hardware. Existing models often prioritize performance, overlooking the issue of complexity. To solve the problems above, we propose a novel Generative Adversarial Network based on Two-Stage Mask Transformer and information Interaction (TSMGAN-II), consisting of an attention encoder, a two-stage mask transformer, and a dual-feature decoder with information interaction. It effectively captures and models both amplitude and spectral characteristics within the time-frequency domain. Experiments on the VoiceBank+DEMAND dataset show that our model, with 1.39 million parameters, achieves state-of-the-art performance with PESQ of 3.40 and SSNR of 11.81. Moreover, we also introduce a lightweight model with just 0.59M parameters, achieving 97% of the performance of SOTA models with PESQ of 3.31 and SSNR of 11.53.
With the development of Artificial Intelligence (AI) and Internet of Things (IoT) technologies, network communications based on the Shannon-Nyquist theorem gradually reveal their limitations due to the neglect of sema...
详细信息
This paper proposes a sliding mode control strategy for balancing the State of Charge (SoC) in lithium-ion battery packs. By thoroughly analyzing the battery balancing circuit topology, a bidirectional Cuk circuit bal...
详细信息
In Mobile sensor Networks, Each and every wireless node dynamically changes its location due to its mobility nature. The routing information is maintained by the master node to deliver a data packet from source to des...
详细信息
The large-scale matrix eigenvalue computation, as a basic mathematical tool, has been widely used in many fields such as face recognition and data analysis. However, local terminal devices lack sufficient resources to...
详细信息
ISBN:
(纸本)9798350348439;9798350384611
The large-scale matrix eigenvalue computation, as a basic mathematical tool, has been widely used in many fields such as face recognition and data analysis. However, local terminal devices lack sufficient resources to undertake heavy computational tasks, which poses a challenge to the applications of eigenvalue computation. In this paper, we propose the first privacy-preserving edge-assisted computation scheme for solving the largest eigenvalue and corresponding eigenvector. We propose a privacy-preserving transformation method to protect data privacy and prevent edge servers from retrieving sensitive information. Meanwhile, we design a verification scheme to ensure the correctness of the results returned by the edge servers. In addition, we design a distributed parallel computing scheme to ensure the efficiency of edge computation. Through theoretical analysis and simulation experiments, we verify the feasibility and efficiency of our proposed scheme.
In order to further improve the financial management quality of small and medium-sized enterprises, provide scientific and efficient financial information support for enterprise operation decisions and minimize the pr...
详细信息
Major depressive disorder (MDD) is a common and socially significant psychiatric disorder with extremely complex pathologic mechanisms. In recent years, resting-state functional magnetic resonance imaging (rs-fMRI) ha...
详细信息
With the deepening of the digital transformation of power systems, new service scenarios such as computing power access and interconnection are continuously developing. The electric power communication network urgentl...
详细信息
Human action recognition (HAR) is a computer vision technique used to understand the activity of the action performed in the scene. Computer vision technology has become popular and is applied in various areas like su...
详细信息
Reducing the dangers associated with high-altitude activities requires improving mountain climbers' safety and tracking skills. In this work, an inventive Internet of Things (IoT)-based system is presented to over...
详细信息
暂无评论