检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cui, Zhongjian Cui, Chenrui Wang, Tianrui He, Mengnan Shi, Hao Ge, Meng Gong, Caixia Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University Tianjin China DiDi Chuxing Beijing China Graduate School of Informatics Kyoto University Kyoto Japan Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

The information loss or distortion caused by single-channel speech enhancement (SE) harms the performance of automatic speech recognition (ASR). Observation addition (OA) is an effective post-processing method to improve ASR performance by balancing noisy and enhanced speech. Determining the OA coefficient is crucial. However, the currently supervised OA coefficient module, called the bridging module, only utilizes simulated noisy speech for training, which has a severe mismatch with real noisy speech. In this paper, we propose training strategies to train the bridging module with real noisy speech. First, DNSMOS is selected to evaluate the perceptual quality of real noisy speech with no need for the corresponding clean label to train the bridging module. Additional constraints during training are introduced to enhance the robustness of the bridging module further. Each utterance is evaluated by the ASR back-end using various OA coefficients to obtain the word error rates (WERs). The WERs are used to construct a multidimensional vector. This vector is introduced into the bridging module with multi-task learning and is used to determine the optimal OA coefficients. The experimental results on the CHiME-4 dataset show that the proposed methods all had significant improvement compared with the simulated data trained bridging module, especially under real evaluation sets. © 2025, CC BY.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models

arXiv

引用

arXiv 2025年

作者： Wang, Tianrui Ge, Meng Gong, Cheng Qiang, Chunyu Wang, Haoyu Huang, Zikang Jiang, Yu Wang, Xiaobao Chen, Xie Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy Guangdong China China Telecom Beijing China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Co. Ltd Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong China

Recently, emotional speech generation and speaker cloning have garnered significant interest in text-to-speech (TTS). With the open-sourcing of codec language TTS models trained on massive datasets with large-scale parameters, adapting these general pre-trained TTS models to generate speech with specific emotional expressions and target speaker characteristics has become a topic of great attention. Common approaches, such as full and adapter-based fine-tuning, often overlook the specific contributions of model parameters to emotion and speaker control. Treating all parameters uniformly during fine-tuning, especially when the target data has limited content diversity compared to the pre-training corpus, results in slow training speed and an increased risk of catastrophic forgetting. To address these challenges, we propose a characteristic-specific partial fine-tuning strategy, short as CSP-FT. First, we use a weighted-sum approach to analyze the contributions of different Transformer layers in a pre-trained codec language TTS model for emotion and speaker control in the generated speech. We then selectively fine-tune the layers with the highest and lowest characteristic-specific contributions to generate speech with target emotional expression and speaker identity. Experimental results demonstrate that our method achieves performance comparable to, or even surpassing, full fine-tuning in generating speech with specific emotional expressions and speaker identities. Additionally, CSP-FT delivers approximately 2× faster training speeds, fine-tunes only around 8% of parameters, and significantly reduces catastrophic forgetting. Furthermore, we show that codec language TTS models perform competitively with self-supervised models in speaker identification and emotion classification tasks, offering valuable insights for developing universal speech processing models. © 2025, CC BY.

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. 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

VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1849-1861页

作者： Chunyu Qiang Wang Geng Yi Zhao Ruibo Fu Tao Wang Cheng Gong Tianrui Wang Qiuyu Liu Jiangyan Yi Zhengqi Wen Chen Zhang Hao Che Longbiao Wang Jianwu Dang Jianhua Tao School of New Media and Communication Tianjin University Tianjin China Kuaishou Technology Company Ltd. Beijing China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Migu Culture Technology Company Ltd. Beijing China Huiyan Technology (Tianjin) Company Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Science Guangdong China

Deep learning has brought significant improvements to the field of cross-modal representation learning. For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired, emphasizing the semantic content of the text modality while de-emphasizing the paralinguistic information of the speech modality. We propose a method called “Vector Quantized Contrastive Token-Acoustic Pre-training (VQ-CTAP)”, which uses the cross-modal aligned sequence transcoder to bring text and speech into a joint multimodal space, learning how to connect text and speech at the frame level. The proposed VQ-CTAP is a paradigm for cross-modal sequence representation learning, offering a promising solution for fine-grained generation and recognition tasks in speech processing. The VQ-CTAP can be directly applied to VC and ASR tasks without fine-tuning or additional structures. We propose a sequence-aware semantic connector, which connects multiple frozen pre-trained modules for the TTS task, exhibiting a plug-and-play capability. We design a stepping optimization strategy to ensure effective model convergence by gradually injecting and adjusting the influence of various loss components. Furthermore, we propose a semantic-transfer-wise paralinguistic consistency loss to enhance representational capabilities, allowing the model to better generalize to unseen data and capture the nuances of paralinguistic information. In addition, VQ-CTAP achieves high-compression speech coding at a rate of 25 Hz from 24 kHz input waveforms, which is a 960-fold reduction in the sampling rate. The experimental results demonstrate that while VQ-CTAP outperforms baseline methods in TTS and VC tasks, its performance on ASR tasks is suboptimal.

关键词： Semantics Training Representation learning Speech recognition Decoding Acoustics Speech coding Speech processing Data mining Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A method to evaluate the spatial extensibility of a switching unit and network

引用

Science China(Information Sciences) 2014年第2期57卷 140-156页

作者： ZHANG Bo WU JunTing WANG BinQiang LI Hui National Digital Switching System Engineering Technological R&D Center Shenzhen Key Lab of Cloud Computing Technology and Application

Switching units and networks have been analyzed as extensible fabrics,mostly in terms of their scheduling *** traditional literature on switching extensibility has provided complexity theory only relating to the total numbers of inputs(or outputs)and exchange *** paper analyzes switching extensibility in terms of not only the scheduling algorithm and also the fabric *** is found that determining extensibility from soft complexity related to the number of inputs(or outputs)of the scheduling algorithm and the fabric extensibility in previous studies without quantization is a flawed conception.A method is thus proposed to express the spatial extensibility of a switching unit or network in terms of the connections of a switching resource and *** method calculates parameter ES(the efciency of switching)of an m×n switching unit and obtains two functions of the switching unit to describe spatial extensibility along with the number of unilateral inputs or *** is found that the range of ES is(0,1]and three types of switching unit and two types of crosspoint networks have ES=*** is calculated for banyan,Clos,parallel packet,fully interconnected and recirculation switching *** ES value for the banyan switching network is larger than that for other networks,and switching networks are classified into three types that have absolute/linear/denied spatial extensibility according to the limES *** is demonstrated that a switching network has the largest ES value when it contains only the five types of switching unit for which ES=***,a group-switching-first self-routing banyan switching network with lower blocking probability and time delay is deduced,and the ES method is contrasted with two other methods of evaluating spatial extensibility in terms of their mathematical expressions and intuitive graphics,for the five types of switching network listed above.

关键词： spatial extensibility connection state efciency of switching banyan fully interconnected recirculation switching network

来源：评论

学校读者我要写书评

暂无评论

InfoMall: A large-scale storage system for web archiving

InfoMall: A large-scale storage system for web archiving

引用

14th International Conference on Web-Age Information Management, WAIM 2013

作者： Huang, Lian'en Li, Jinping Li, Xiaoming Shenzhen Key Laboratory for Cloud Computing Application and Technology Peking University Shenzhen Graduate School Shenzhen Gongdong 518055 China

ISBN: (纸本)9783642395260

The World Wide Web is a fluid medium which means that Web pages or entire Web sites frequently change or disappear, often without leaving any trace. Considering the great value of the Web, it is quite necessary to archive the current Web for the future. In order to do this, a large-scale storage system is required. In this paper we propose such a system which is designed for storing the massive Web pages we have been collecting consistently since 2001. One significant feature of this collection of Web pages is that it is space-time dimensioned which means every Web page is attached with a URL and a time, while one URL is possible to contain lots of Web pages crawled at different times. Our system is designed that sorted Web pages are clustered and stored together by some degree of space-time granularity. As a result, users are able to retrieve effectively Web pages with URLs and times specified or batches of Web pages with URL ranges and time ranges specified. © 2013 Springer-Verlag.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

O2iJoin： An Efficient Index-Based Algorithm for Overlap Interval Join

引用

Journal of Computer Science & technology 2018年第5期33卷 1023-1038页

作者： Ji-Zhou Luo Sheng-Fei Shi Guang Yang Hong-Zhi Wang Jian-Zhong Li School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China Guangdong Key Laboratory of Popular High Performance Computers Key Laboratory of Service Computing and Application Shenzhen 518000 China

Time intervals are often associated with tuples to represent their valid time in temporal relations, where overlap join is crucial for various kinds of queries. Many existing overlap join algorithms use indices based on tree structures such as quad-tree, B＋-tree and interval tree. These algorithms usually have high CPU cost since deep path traversals are unavoidable, which makes them not so competitive as data-partition or plane-sweep based algorithms. This paper proposes an efficient overlap join algorithm based on a new two-layer flat index named as Overlap Interval Inverted Index （i.e., O2i Index）. It uses an array to record the end points of intervals and approximates the nesting structures of intervals via two functions in the first layer, and the second layer uses inverted lists to trace all intervals satisfying the approximated nesting structures. With the help of the new index, the join algorithm only visits the must-be-scanned lists and skips all others. Analyses and experiments on both real and synthetic datasets show that the proposed algorithm is as competitive as the state-of-the-art algorithms.

关键词： overlap interval join temporal relation overlap inverted index join algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on cancer rapid diagnosis technology based on adaptive channel attention mechanism and two-dimensional spectral fusion

引用

Microchemical Journal 2025年 213卷

作者： Wei Liu Chenjie Chang Jiahe Li Xiaoyi Lv Yang Liu Chen Chen Cheng Chen College of Software Xinjiang University Urumqi 830046 China School of Computer Science and Technology Xinjiang University Urumqi 830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang Cloud Computing Engineering Technology Research Center Karamay 834000 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi 830046 China

With the widespread use of Artificial Intelligence (AI) in biomedicine, integrating infrared and Raman spectra with biological information offers new prospects for enhanced disease diagnosis. For these two types of data, more information can be extracted using multimodal data fusion compared to single modality, but existing studies tend to only fuse one-dimensional spectral data, ignoring the richer information of the spectra when they are converted to two-dimensional images. In this study, we propose a rapid diagnostic method for cancer, which first converts one-dimensional (1D) Raman and Infrared spectra into two-dimensional (2D) spectral images using Short-Time Fourier Transform (STFT), respectively. Then the features are fused by our designed Adaptive Graph Channel Attention Spacial Cross-Attention Fusion Module (ASCFM). This fusion module innovatively uses the adaptive graph channel attention mechanism to strengthen the model’s ability to capture the key information of different spectral features, and utilizes the spatial attention fusion module and the cross-attention module for spatial information extraction and fusion. The output fused features effectively avoid feature information loss through this multimodal feature extraction and fusion, which greatly improves the performance of the model. In this study, Gradient-weighted Class Activation Mapping is also used to make the decision-making process of the neural network more interpretable. The results show that the accuracy of 2D Raman spectral images fused with 2D infrared spectral images by ASCFM followed by ResidualNetwork (ResNet) for diagnosis of lung cancer and glioma datasets is 98.88 % and 96.38 %, which suggests that it is a highly promising adjunctive technique for cancer diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Telemedicine technology and Implement based on Virtual Reality

Research on Telemedicine Technology and Implement based on V...

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Hong Ji Jing Wang Jia Gao Xiaohui Liu Virtual Reality Department Beijing Computing Center Beijing Key Laboratory of cloud computing key technology and application

ISBN: (纸本)9781509001668

This paper researched the key technologies and implementation methods of virtual telemedicine,in which the Virtual Reality,cloud computing,Communication and modern medical technologies are comprehensively *** virtual telemedicine is different from traditional medical which is out of the constraints of time and *** cloud architecture technology to design a remote cooperative medical application system based on virtual reality technology,which ensure that the medical diagnostic information could be presented and reproduced by 3D visualization models,and the system is crossplatform,many people sharing,synergetic and *** sharing and remote rapid consultation are implemented through remote real-time multiplayer sharing diagnosis based on 3D human anatomy model information,which use of cloud computing,secure communication,virtual reality technology and medical equipment to share data,text,voice and image data.

关键词： Telemedicine Virtual Reality collaborative diagnosis and treatment Share 3D Scene

来源：评论

学校读者我要写书评

暂无评论

A synchronous algorithm of network coding with hardware logic

A synchronous algorithm of network coding with hardware logi...

引用

Symposium on ICT and Energy Efficiency and Workshop on Information Theory and Security, CIICT 2012

作者： Li, Jiang Li, Yining Li, Hui Zhu, Zhipu Zhang, Huayu Chen, Fuxing Shenzhen Key Lab. of Cloud Computing Technology and Application Shenzhen Graduate School Peking University Shenzhen 518055 China

ISBN: (纸本)9781849195478

This paper presents an efficient hardware prototype for network coding (NC). First, a packet synchronization mechanism is introduced to settle the problem of packet arriving mismatch between different incoming channels. Then a high-speed lookup-table-based circuit is designed to perform dot product over Galois Field, which forms the basic calculation unit of NC operation. Taking the speed advantage of FPGA hardware, this prototype is able to perform network coding operations within several hundred nanoseconds. Thus further studies and emulations on NC are able to be carried out upon this platform in the real network scenario.

关键词： Network coding

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：