检索结果-内蒙古大学图书馆

A Framework Combining Separate and Joint Training for Neural Vocoder-Based Monaural Speech Enhancement 1

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Pan, Qiaoyi Jiang, Wenbing Zhuo, Qing Yu, Kai Shanghai Jiao Tong University Shanghai China School of Communication Engineering Hangzhou Dianzi University Hangzhou China Department of Automation Tsinghua University Beijing China MoE Key Lab of Artificial Intelligence X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9789819706013

ISBN: (纸本)9789819706006

Conventional single-channel speech enhancement methodologies have predominantly emphasized the enhancement of the amplitude spectrum while preserving the original phase spectrum. Nonetheless, this may introduce speech distortion. While the intricate nature of the multifaceted spectra and waveform characteristics presents formidable challenges in training. In this paper, we introduce a novel framework with the Mel-spectrogram serving as an intermediary feature for speech enhancement. It integrates a denoising network and a deep generative network vocoder, allowing the reconstruction of the speech without using the phase. The denoising network, constituting a recurrent convolutional autoencoder, is meticulously trained to align with the Mel-spectrogram representations of both clean and noisy speech, resulting in an enhanced spectral output. This enhanced spectrum serves as the input for a high-fidelity, high-generation speed vocoder, which synthesizes the improved speech waveform. Following the pre-training of these two modules, they are stacked for joint training. Experimental results show the superiority of this approach in terms of speech quality, surpassing the performance of conventional models. Notably, our method demonstrates commendable adaptability across both the Chinese dataset CSMSC and the English language speech dataset VoiceBank+DEMAND, underscoring its considerable promise for real-world applications and beyond. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Incremental SDN Deployment to Achieve Load Balance in ISP Networks 16th

Incremental SDN Deployment to Achieve Load Balance in ISP ...

引用

16th International Conference on Algorithmic Aspects in Information and Management, AAIM 2022

作者： Cheng, Yunlong Zhou, Hao Gao, Xiaofeng Zheng, Jiaqi Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9783031160806

Software defined network (SDN) decouples control planes from data planes and integrates them into a logically centralized controller. With capture of the global view, the controller can dynamically and timely reply to the changes of network states. However, replacing the entire traditional networks, e.g., Internet Service Provider (ISP) networks, with SDNs is difficult and computationally expensive. Hence, incremental deployment of partial SDN devices has received much attention. In this paper, we consider the k-LB problem, i.e., upgrading at most k legacy switches to SDN switches to achieve load balance. We claim that k-LB problem is NP-hard and there is no polynomial time (N+ M) 1-ϵ -approximation algorithm for any constant ϵ> 0 unless P= NP, where N (M) is the number of switches (links) in the network. Given these negative results, we propose an effective greedy algorithm and claim that it reaches an approximation guarantee of cavgcminM, where cavg (cmin ) is the average (minimum) link capacity. Large-scale simulations on real ISP networks show that our greedy algorithm achieves near optimal performance and decreases the maximum link utilization by 30% on average compared with the state of the art. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models

Look Before You Leap: Problem Elaboration Prompting Improves...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liao, Haoran Tian, Jidong Hu, Shaohua Zhu, Zhihao He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

Large language models (LLMs) still grapple with complex tasks like mathematical reasoning. Despite significant efforts invested in improving prefix prompts or reasoning process, the crucial role of problem context might have been neglected. Accurate recognition of inputs is fundamental for solving mathematical tasks, as ill-formed problems could potentially mislead LLM's reasoning. In this study, we propose a new approach named Problem Elaboration Prompting (PEP) to enhance the mathematical capacities of LLMs. Specifically, PEP decomposes and elucidates the problem context before reasoning, therefore enhancing the context modeling and parsing efficiency. Experiments across datasets and models demonstrate promising performances: (1) PEP demonstrates an overall enhancement in various situation. (2) PEP can be easily implemented and integrated with other prompting methods. (3) PEP shows particular strength in handling distraction problems. © 2025 IEEE.

关键词： Cognitive science Large Language Models Mathematical Reasoning Semantic Parsing

来源：评论

学校读者我要写书评

暂无评论

Mixture of link predictors on graphs 24

Mixture of link predictors on graphs

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Li Ma Haoyu Han Juanhui Li Harry Shomer Hui Liu Xiaofeng Gao Jiliang Tang MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Michigan State University

ISBN: (纸本)9798331314385

Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models that only apply the same pairwise information uniformly could achieve suboptimal performance. As a result, we propose a simple mixture of experts model Link-moe for link prediction. Link-moe utilizes various GNNs as experts and strategically selects the appropriate expert for each node pair based on various types of pairwise information. Experimental results across diverse real-world datasets demonstrate substantial performance improvement from Link-moe. Notably, Link-moe achieves a relative improvement of 18.71% on the MRR metric for the Pubmed dataset and 9.59% on the Hits@100 metric for the ogbl-ppa dataset, compared to the best baselines. The code is available at https://***/ml-ml/Link-moe/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GeoMix: Towards Geometry-Aware Data Augmentation

arXiv

引用

arXiv 2024年

作者： Zhao, Wentao Wu, Qitian Yang, Chenxiao Yan, Junchi Shanghai Jiao Tong University Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai China

Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of features and labels, Mixup effectively addresses the issue of data scarcity. However, it has rarely been explored in graph learning tasks due to the irregularity and connectivity of graph data. Specifically, in node classification tasks, Mixup presents a challenge in creating connections for synthetic data. In this paper, we propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing. It effectively utilizes geometry information to interpolate features and labels with those from the nearby neighborhood, generating synthetic nodes and establishing connections for them. We conduct theoretical analysis to elucidate the rationale behind employing geometry information for node Mixup, emphasizing the significance of locality enhancement—a critical aspect of our method’s design. Extensive experiments demonstrate that our lightweight Geometric Mixup achieves state-of-the-art results on a wide variety of standard datasets with limited labeled data. Furthermore, it significantly improves the generalization capability of underlying GNNs across various challenging out-of-distribution generalization tasks. Our code is available at https://***/WtaoZhao/geomix. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Extinction Chains Reveal Intermediate Phases Between the Safety and Collapse in Mutualistic Ecosystems

引用

engineering 2024年第12期43卷 89-98页

作者： Guangwei Wang Xueming Liu Ying Xiao Ye Yuan Linqiang Pan Xiaohong Guan Jianxi Gao Hai-Tao Zhang The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Digital Manufacturing Equipment and TechnologySchool of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Guangdong HUST Industrial Technology Research Institute Huazhong University of Science and TechnologyDongguan 523808China Guangdong Provincial Engineering Technology Center of Autonomous Unmanned Vessels Dongguan 523808China MOE Key Laboratory of Intelligent Networks and Network Security&State Key Laboratory of Manufacturing Systems Xi’an Jiaotong UniversityXi’an 710049China Tsinghua National Laboratory of Information Science and Technology Department of AutomationTsinghua UniversityBeijing 100084China Department of Computer Science Rensselaer Polytechnic InstituteTroyNY 12180USA

Ecosystems are undergoing unprecedented persistent deterioration due to unsustainable anthropogenic human activities,such as overfishing and deforestation,and the effects of such damage on ecological stability are *** recent advances in experimental and theoretical studies on regime shifts and tipping points,theoretical tools for understanding the extinction chain,which is the sequence of species extinctions resulting from overexploitation,are still lacking,especially for large-scale nonlinear networked *** this study,we developed a mathematical tool to predict regime shifts and extinction chains in ecosystems under multiple exploitation situations and verified it in 26 real-world mutualistic networks of various sizes and *** discovered five phases during the exploitation process:safe,partial extinction,bistable,tristable,and collapse,which enabled the optimal design of restoration strategies for degraded or collapsed *** validated our approach using a 20-year dataset from an eelgrass restoration ***,we also found a specific region in the diagram spanning exploitation rates and competition intensities,where exploiting more species helps increase *** computational tool provides insights into harvesting,fishing,exploitation,or deforestation plans while conserving or restoring the biodiversity of mutualistic ecosystems.

关键词： Complex system Network science Overexploitation Regime shift Metastability

来源：评论

学校读者我要写书评

暂无评论

DITune: A Reinforcement Learning Based Framework for Automated Database Index Selection

DITune: A Reinforcement Learning Based Framework for Automat...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Xiuqi Huang Xiaofeng Gao Guihai Chen Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China

Index selection is a crucial and essential aspect of database management systems (DBMS) aiming to optimize performance, and it is also one of the most time-consuming and laborious tasks for database administrators (DBAs). Therefore, automatic methods and tools are urgently needed to help DBAs choose a good index configuration for workloads. We propose a recommender system named DITune (Database Index Tuning) which can automatically analyze workloads, explore the potential benefits of indexes, and adjust the index configuration. We first implement a rule-based method to embed the database workload and data distribution feature. Then we utilize the Deep Deterministic Policy Gradient (DDPG) algorithm to generate index recommendations and construct index configuration. Moreover, we design a benchmark based on the standard TPC-C to validate the performance of our method under the varying workload patterns, query complexity, and running phase length. The experiment results show the effectiveness and robustness of DITune and indicate that the data-driven prediction outperforms those models based on cost estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation

Generalizable Audio Deepfake Detection via Latent Space Refi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Wen Gu, Yanmei Wang, Zhiming Zhu, Huijia Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology Shanghai China Ant Group Shanghai China

ISBN: (纸本)9798350368741

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a novel strategy that integrates Latent Space Refinement (LSR) and Latent Space Augmentation (LSA) to improve the generalization of deepfake detection systems. LSR introduces multiple learnable prototypes for the spoof class, refining the latent space to better capture the intricate variations within spoofed data. LSA further diversifies spoofed data representations by applying augmentation techniques directly in the latent space, enabling the model to learn a broader range of spoofing patterns. We evaluated our approach on four representative datasets, i.e. ASVspoof 2019 LA, ASVspoof 2021 LA and DF, and In-The-Wild. The results show that LSR and LSA perform well individually, and their integration achieves competitive results, matching or surpassing current state-of-the-art methods. © 2025 IEEE.

关键词： anti-spoofing audio deepfake detection generalization

来源：评论

学校读者我要写书评

暂无评论

Incomplete intuitionistic fuzzy behavioral group decision-making based on multigranulation probabilistic rough sets and MULTIMOORA for water quality inspection

引用

Journal of Intelligent and Fuzzy Systems 2023年第3期44卷 4537-4556页

作者： Bai, Wenhui Zhang, Chao Zhai, Yanhui Sangaiah, Arun Kumar School of Computer and Information Technology Key Lab. of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

Water quality inspection (WQI) is one of the primary ways to ensure the safe utilization of water resources, and complicated data modeling, fusion and analysis play a significant role in seeking the resource with the best water quality. Nevertheless, the challenges of missing data, relatively large differences in decision results and bounded rationality owned by decision-makers (DMs) in terms of WQI still exist nowadays. Thus, from the aspect of stable and behavioral decision-making in multi-granularity incomplete intuitionistic fuzzy information systems (MG-IIFISs), the paper investigates a comprehensive multi-attribute group decision-making (MAGDM) approach for the application of WQI. First, the concept of MG-IIFISs is built by modeling MAGDM problems with intuitionistic fuzzy numbers (IFNs), then a new transformation scheme is constructed for transforming MG-IIFISs into multi-granularity intuitionistic fuzzy information systems (MG-IFISs) based on the similarity principle. Second, three types of multigranulation intuitionistic fuzzy probabilistic rough sets (MG IF PRSs) are developed by referring to the MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form) method. Afterwards, attribute weights are objectively calculated based on the best-worst method (BWM), and a new stable and behavioral MAGDM approach is constructed by means of the TODIM (an acronym in Portuguese for interactive multi-criteria decision-making) method. At last, a case study in the setting of WQI is conducted with the support of a UCI data set, and sensitivity analysis, comparative analysis and experimental analysis are investigated to display the validity of the proposed approach. In general, the proposed approach improves the stability of decision results via MULTIMOORA and BWM, and also fully considers the bounded rationality of DMs' psychological behaviors from the aspect of the TODIM method, which has certain advantages in the community of MAGDM studie

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

HUSS:A Heuristic Method for Understanding the Semantic Structure of Spreadsheets

引用

Data intelligence 2023年第3期5卷 537-559页

作者： Xindong Wu Hao Chen Chenyang Bu Shengwei Ji Zan Zhang Victor S.Sheng Key Laboratory of Knowledge Engineering with Big Data(the Ministry of Education of China) Hefei University of TechnologyChinaSchool of Computer Science and Information EngineeringHefei University of TechnologyHefeiChina Research Institute of Artificial Intelligence Zhejiang LabHangzhouChina Department of Computer Science Texas Tech UniversityLubbockTX 79409USA

Spreadsheets contain a lot of valuable data and have many practical *** key technology of these practical applications is how to make machines understand the semantic structure of spreadsheets,e.g.,identifying cell function types and discovering relationships between cell *** existing methods for understanding the semantic structure of spreadsheets do not make use of the semantic information of cells.A few studies do,but they ignore the layout structure information of spreadsheets,which affects the performance of cell function classification and the discovery of different relationship types of cell *** this paper,we propose a Heuristic algorithm for Understanding the Semantic Structure of spreadsheets(HUSS).Specifically,for improving the cell function classification,we propose an error correction mechanism(ECM)based on an existing cell function classification model[11]and the layout features of *** improving the table structure analysis,we propose five types of heuristic rules to extract four different types of cell pairs,based on the cell style and spatial location *** experimental results on five real-world datasets demonstrate that HUSS can effectively understand the semantic structure of spreadsheets and outperforms corresponding baselines.

关键词： Spreadsheet semantic structure Information extraction Heuristics Cell function analysis Table structure analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：