Diffusion-based speech enhancement (SE) models have recently demonstrated superior performance compared to traditional single-step models. In this work, we revisit the advantages of diffusion models from a multi-source learning perspective, highlighting that their ability to jointly leverage data likelihood and conditional mapping makes them theoretically superior to deterministic models when controllability is ensured. From this standpoint, we identify a key limitation in DOSE, a recent diffusion-based SE model that enhances controllability by applying fixed dropout ratio to non-conditional inputs, leading to unnecessary information loss at every timestep. To address this, we propose a timestep-aware dropout mechanism that dynamically adjusts the dropout intensity at each denoising step. Extensive experiments across matched and cross-dataset benchmarks show that our method consistently outperforms DOSE and other state-of-the-art diffusion-based SE methods, achieving superior speech enhancement with high efficiency. The code and audio samples are publicly available athttps://github.com/ICDM-UESTC/DOSE.

Diffusion models have shown great potential for super-resolution by effectively mapping high-resolution images from low-resolution inputs. However, the heavy inference cost remains a significant challenge. In this work, we propose Efficient self-correcting Diffusion Bridge (EDB), a novel framework for diffusion bridge-based super-resolution. EDB introduces two key components: non-Markovian implicit sampling to improve sampling efficiency and self-correcting training to reduce estimation error. Applied to image super-resolution (SR), EDB effectively balances enhanced sampling efficiency with high image quality. Extensive quantitative and qualitative comparisons with advanced methods reveal that our method achieves competitive or even superior super-resolution performance metrics with higher sampling efficiency, highlighting its capability for accurate and efficient super-resolution of degraded images.

Instead of using a standard diffusion model, most diffusion-based speech enhancement methods additionally incorporate a mean interpolation strategy into the diffusion process. However, the role and impact of this strategy remain unclear. In this study, we investigate mean interpolation from a data augmentation perspective, demonstrating that it serves as a specific form of distribution augmentation and provides a unified formula for mean interpolation, which encompasses current variations of such strategy. Building on this insight, we propose DANS (Distribution Augmentation with Noise Shuffling), an advanced distribution augmentation method that further expands the training distribution through noise-shuffling techniques. Experimental results show that DANS consistently outperforms existing methods in matched, cross-dataset, and low-data scenarios. Codes are publicly available at https://github.com/ICDM-UESTC/DANCE.

This paper proposes a systematic approach to designing industrial device function models using AutomationML (AML) aligned with the Asset Administration Shell (AAS) framework. The methodology addresses the challenges of multi-domain data integration, cross-platform interoperability, and dynamic adaptability in Industry 4.0 environments. By leveraging AML’s XML-based engineering data exchange capabilities and AAS’s standardized digital twin architecture, the proposed model achieves seamless integration of mechanical, electrical, control, and semantic information. At the end, we design the use case by the AML-AAS tools to verify the function.

The product information generated at different levels in the automated manufacturing process is closely related to the final product information. This paper is to sort out the types of product information in the automated manufacturing process between China and Germany, and compared the structure and interfaces of product information integration, and research the key technical support for the application of product information and analysis for the use case.

Amid the rapid development of e-commerce and logistics, enterprises urgently require advanced digital technologies to achieve modernization and intelligent transformation, thereby meeting the fast-changing market demands. Within the logistics Internet of Things (IoT), companies face numerous scenarios that necessitate quantifying the degree of data overlap, where only acquiring statistical information suffices. The Private Set Intersection Cardinality (PSI-CA) technology offers an almost ideal solution. However, an effective approach must not only safeguard privacy but also enable companies to demonstrate their data protection capabilities to consumers. Existing PSI-CA solutions neglect the sustainable development needs of enterprises in terms of data correctness, integrity, management transparency, and user retention. Therefore, this paper proposes, for the first time, a trackable and verifiable authorized cloud-assisted PSI-CA (TVACPSI-CA) protocol, upon which a multi-threaded intelligent logistics system (ILS) is designed to harmonize data privacy protection with operational efficiency in logistics enterprises. The protocol employs accumulators, oblivious pseudorandom function (OPRF), zero-knowledge proof, digital signatures and blockchain technology to achieve objectives such as data privacy protection, access control, correctness verification of delegated computation, data integrity protection, abuse resistance, and traceability. This facilitates enterprises in mitigating security risks and enhancing customer trust. We rigorously analyze and prove the security of our solution. Finally, a comparative analysis with existing approaches demonstrates that the proposed scheme balances between high security and low communication/computational overhead. This provides the logistics industry with a secure, efficient, and scalable data-sharing solution, thereby enabling operational optimization.

Recent advancements in generative modeling have successfully integrated denoising diffusion probabilistic models (DDPMs) into the domain of speech enhancement (SE). Despite their considerable advantages in generalizability, ensuring semantic consistency of the generated samples with the condition signal remains a formidable challenge. Inspired by techniques addressing posterior collapse in variational autoencoders, we explore skip connections within diffusion-based SE models to improve consistency with condition signals. However, experiments reveal that simply adding skip connections is ineffective and even counterproductive. We argue that the independence between the predictive target and the condition signal causes this failure. To address this, we modify the training objective from predicting random Gaussian noise to predicting clean speech and propose a progressive skip connection strategy to mitigate the decrease in mutual information between the layer's output and the condition signal as network depth increases. Experiments on two standard datasets demonstrate the effectiveness of our approach in both seen and unseen scenarios. The code is publicly available at https://github.com/ICDM-UESTC/SCSE.

Earnings call transcripts hold valuable insights that are vital for investors and analysts when making informed decisions. However, extracting these insights from lengthy and complex transcripts can be a challenging task. The traditional manual examination is not only time-consuming but also prone to errors and biases. Deep learning-based representation learning methods have emerged as promising and automated approaches to tackle this problem. Nevertheless, they may encounter significant challenges, such as the unreliability of the representation encoding process and certain domain-specific requirements in the context of finance. To address these issues, we propose a novel transcript representation learning model. Our model leverages the structural information of transcripts to effectively extract key insights, while endowing model with explainability via variational information bottleneck. Extensive experiments on two downstream financial tasks demonstrate the effectiveness of our approach.

Recently, the field of Speech Enhancement has witnessed the success of diffusion-based generative models. However, these diffusion-based methods used to take multiple iterations to generate high-quality samples, leading to high computational costs and inefficiency. In this paper, we propose SDFEN (Shallow Diffusion for Fast spEech eNhancement), a novel approach for addressing the inefficiency problem while enhancing the quality of generated samples by reducing the iterative steps in the reverse process of diffusion method. Specifically, we introduce the shallow diffusion strategy initiating the reverse process with an adaptive time step to accelerate inference. In addition, a dedicated noisy predictor is further proposed to guide the adaptive selection of time step. Experiment results demonstrate the superiority of the proposed SDFEN in effectiveness and efficiency.

Speech enhancement (SE) aims to improve the intelligibility and quality of speech in the presence of non-stationary additive noise. Deterministic deep learning models have traditionally been used for SE, but recent studies have shown that generative approaches, such as denoising diffusion probabilistic models (DDPMs), can also be effective. However, incorporating condition information into DDPMs for SE remains a challenge. We propose a model-agnostic method called DOSE that employs two efficient condition-augmentation techniques to address this challenge, based on two key insights: (1) We force the model to prioritize the condition factor when generating samples by training it with dropout operation; (2) We inject the condition information into the sampling process by providing an informative adaptive prior. Experiments demonstrate that our approach yields substantial improvements in high-quality and stable speech generation, consistency with the condition factor, and inference efficiency. Codes are publicly available at https://github.com/ICDM-UESTC/DOSE.

WiFi channel state information (CSI)-based activity recognition has initiated a great many studies because of wide availability and privacy protection. However, general recognition approaches still struggle to generalize beyond the source domain of training data, i.e., well-trained models might not be suitable to target data with unseen subjects or environments. Existing solutions, such as few-shot learning-based and data augmentation-based approaches, either require a few labeled target samples which is difficult to be collected, especially, for old target users, or inappropriately treat augmented samples with different amounts of noise. To overcome these limitations, we propose a Mean Teacher-based cross-domain human activity recognition framework using WiFi CSI, WiTeacher. In this framework, to address the shift between source and target domains, we built a label smoothing-based classification loss, where the input data are the target-like samples generated by StyleGAN, and corresponding label values are dynamically adjusted by our designed adaptive label smoothing method. To enhance the model robustness, we devise a sample relation-based consistency regularization term to keep the distances of the two samples with and without perturbations invariant, which can exploit the relationships between samples to improve recognition performance. The experiments illustrate that WiTeacher achieves obvious gains without requiring any annotation data from the target domain.

Graph anomaly detection is attracting remarkable multidisciplinary research interests ranging from finance, healthcare, and social network analysis. Recent advances on graph neural networks have substantially improved the detection performance via semi-supervised representation learning. However, prior work suggests that deep graph-based methods tend to learn spurious correlations. As a result, they fail to generalize beyond training data distribution. In this article, we aim to identify structural and contextual anomaly nodes in an attributed graph. Based on our preliminary data analyses, spurious correlations can be eliminated with causal subgraph interventions. Therefore, we propose a new graph-based anomaly detection model that can learn causal relations for anomaly detection while generalizing to new environments. To handle situations with varying environments, we steer the generative model to manufacture synthetic environment features, which are exerted on realistic subgraphs to generate counterfactual subgraphs. Further, these counterfactual subgraphs help a few-shot anomaly detection model learn transferable and causal relations across different environments. The experiments on three real-world attributed graphs show that the proposed approach achieves the best performance compared to the state-of-the-art baselines and learns robust causal representations resistant to noises and spurious correlations.

Due to its nonintrusive character, WiFi channel state information (CSI)-based activity recognition has attracted tremendous attention in recent years. Since activity recognition performance heavily relies on activity segmentation results, a number of activity segmentation methods have been designed, and most of them focus on seeking optimal thresholds to segment activities. However, these threshold-based methods are strongly dependent on designers' experience and might suffer from performance decline when applying to the scenario, including both fine-grained and coarse-grained activities. To address these challenges, we present DeepSeg, a deep learning-based activity segmentation framework for activity recognition using WiFi signals. In this framework, we transform segmentation tasks into classification problems and propose a CNN-based activity segmentation algorithm, which can reduce the dependence on experience and address the performance degradation problem. To further enhance the overall performance, we design a feedback mechanism, where the segmentation algorithm is refined based on the feedback computed using activity recognition results. The experiments demonstrate that DeepSeg acquires remarkable gains compared with state-of-the-art approaches.