检索结果-内蒙古大学图书馆

Multi-Stage Speaker Extraction with Utterance and Frame-Level Reference Signals

学校读者我要写书评

暂无评论

Multi-Stage Speaker Extraction with Utterance and Frame-Leve...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Meng Ge Chenglin Xu Longbiao Wang Eng Siong Chng Jianwu Dang Haizhou Li Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Engineering Nanyang Technological University Singapore National University of Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan Machine Listening Lab University of Bremen Germany

ISBN: (纸本)9781728176055;9781728176062

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted speech in early stages is used as the reference speech for late stages. For the first time, we use frame-level sequential speech embedding as the reference for target speaker. This is a departure from the traditional utterance-based speaker embedding reference. In addition, a signal fusion scheme is proposed to combine the decoded signals in multiple scales with automatically learned weights. Experiments on WSJ0-2mix and its noisy versions (WHAM! and WHAMR!) show that SpEx++ consistently outperforms other state-of-the-art baselines.

关键词： Conferences Signal processing Acoustics Noise measurement Time-domain analysis Speech processing

When Deep Learning Meets Information Retrieval-based Bug Localization: A Survey

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Niu, Feifei Li, Chuanyi Liu, Kui Xia, Xin Lo, David State Key Laboratory for Novel Software Technology Software Institute Nanjing University Nanjing China Software Engineering Application Technology Lab Huawei Hangzhou China College of Computer Science and Technology Zhejiang University China School of Computing and Information Systems Singapore Management University Singapore

Bug localization is a crucial aspect of software maintenance, running through the entire software lifecycle. Information retrieval-based bug localization (IRBL) identifies buggy code based on bug reports, expediting the bug resolution process for developers. Recent years have witnessed significant achievements in IRBL, propelled by the widespread adoption of deep learning (DL). To provide a comprehensive overview of the current state of the art and delve into key issues, we conduct a survey encompassing 61 IRBL studies leveraging DL. We summarize best practices in each phase of the IRBL workflow, undertake a meta-analysis of prior studies, and suggest future research directions. This exploration aims to guide further advancements in the field, fostering a deeper understanding and refining practices for effective bug localization. Our study suggests that the integration of DL in IRBL enhances the model’s capacity to extract semantic and syntactic information from both bug reports and source code, addressing issues such as lexical gaps, neglect of code structure information, and cold-start problems. Future research avenues for IRBL encompass exploring diversity in programming languages, adopting fine-grained granularity, and focusing on real-world applications. Most importantly, although some studies have started using large language models for IRBL, there is still a need for more in-depth exploration and thorough investigation in this area. © 2025, CC BY.

关键词： Online searching

Real-time Illumination Estimation for Mixed Reality on Mobile Devices

学校读者我要写书评

暂无评论

Real-time Illumination Estimation for Mixed Reality on Mobil...

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Di Xu Zhen Li Yanning Zhang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

We present a lightweight lighting estimation method for the purpose of realistic mixed reality (MR) on mobile devices. Given a single RGB image, our method estimates the environment lighting and renders the virtual object in real-time. While previous works tackled this problem by reconstructing the complicated high dynamic range (HDR) environment maps, our deep neural network directly infers the corresponding spherical harmonics in extensive environments. Compared to previous approaches, our method is more robust and efficient as it works for both indoor and outdoor scenes in real-time. Experiments show that our approach achieves realistic rendering in various MR scenarios.

关键词： Lighting Virtual reality Real-time systems Mobile handsets Estimation Robustness Image reconstruction

A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics, and Benchmark Datasets

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zeng, Chengchang Li, Shaobo Li, Qin Hu, Jie Hu, Jianjun Chengdu Institute of Computer Application University of Chinese Academy of Sciences School of Mechanical Engineering Guizhou University College of Big Data and Statistics GuiZhou University of Finance and Economics Department of Computer Science and Engineering University of South Carolina

Machine Reading Comprehension (MRC) is a challenging NLP research field with wide real world applications. The great progress of this field in recent years is mainly due to the emergence of large-scale datasets and deep learning. At present, a lot of MRC models have already surpassed the human performance on many datasets despite the obvious giant gap between existing MRC models and genuine human-level reading comprehension. This shows the need of improving existing datasets, evaluation metrics and models to move the MRC models toward’real’ understanding. To address this lack of comprehensive survey of existing MRC tasks, evaluation metrics and datasets, herein, (1) we analyzed 57 MRC tasks and datasets;proposed a more precise classification method of MRC tasks with 4 different attributes (2) we summarized 9 evaluation metrics of MRC tasks and (3) 7 attributes and 10 characteristics of MRC datasets;(4) We also discussed some open issues in MRC research and highlight some future research directions. In addition, to help the community, we have collected, organized, and published our data on a companion website(https://***/) where MRC researchers could directly access each MRC dataset, papers, baseline projects and browse the leaderboard. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

How likely is a random graph shift-enabled?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Liyan Cheng, Samuel Stankovic, Vladimir Stankovic, Lina Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhejiang Zhoushan316022 China Department of Computer Science and Technology Tongji University Shanghai201804 China School of Electrical and Computer Engineering University of Oklahoma OK74105 United States Department of Electronic and Electrical Engineering University of Strathclyde GlasgowG1 1XW United Kingdom

The shift-enabled property of an underlying graph is essential in designing distributed filters. This article discusses when a random graph is shift-enabled. In particular, popular graph models Erdős–Rényi (ER), Watts–Strogatz (WS), Barabási–Albert (BA) random graph are used, weighted and unweighted, as well as signed graphs. Our results show that the considered unweighted connected random graphs are shift-enabled with high probability when the number of edges is moderately high. However, very dense graphs, as well as fully connected graphs, are not shift-enabled. Interestingly, this behaviour is not observed for weighted connected graphs, which are always shift-enabled unless the number of edges in the graph is very low. © 2021, CC BY.

关键词： Signal processing

Rate-induced tipping in complex high-dimensional ecological networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Panahi, Shirin Do, Younghae Hastings, Alan Lai, Ying-Cheng School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Department of Mathematics Nonlinear Dynamics & Mathematical Application Center Kyungpook National University Daegu41566 Korea Republic of Department of Environmental Science and Policy University of California One Shields Avenue DavisCA95616 United States Santa Fe Institute 1399 Hyde Park Road Santa FeNM87501 United States Department of Physics Arizona State University TempeAZ85287 United States

In an ecosystem, environmental changes as a result of natural and human processes can cause some key parameters of the system to change with time. Depending on how fast such a parameter changes, a tipping point can occur. Existing works on rate-induced tipping, or R-tipping, offered a theoretical way to study this phenomenon but from a local dynamical point of view, revealing, e.g., the existence of a critical rate for some specific initial condition above which a tipping point will occur. As ecosystems are subject to constant disturbances and can drift away from their equilibrium point, it is necessary to study R-tipping from a global perspective in terms of the initial conditions in the entire relevant phase space region. In particular, we introduce the notion of the probability of R-tipping defined for initial conditions taken from the whole relevant phase space. Using a number of real-world, complex mutualistic networks as a paradigm, we discover a scaling law between this probability and the rate of parameter change and provide a geometric theory to explain the law. The real-world implication is that even a slow parameter change can lead to a system collapse with catastrophic consequences. In fact, to mitigate the environmental changes by merely slowing down the parameter drift may not always be effective: only when the rate of parameter change is reduced to practically zero would the tipping be avoided. Our global dynamics approach offers a more complete and physically meaningful way to understand the important phenomenon of R-tipping. © 2023, CC BY.

关键词： Ecosystems

Error Correction of Tibetan Verbs Based on Deep Learning

学校读者我要写书评

暂无评论

Error Correction of Tibetan Verbs Based on Deep Learning

Artificial Intelligence and computer engineering (ICAICE), International Conference on

作者： HUA Guo‒ cai– rang Secha Jia BAN Ma– bao CAI Rang– jia School of computer science Qinghai Normal University China Qinghai Key Laboratory of Tibetan information processing and machine translation China Qinghai Tibetan information processing engineering technology research center China State Key Laboratory of Tibetan intelligent information processing and application China

Verbs are the core of the semantic structure represented by Tibetan sentences, and automatic error correction of Tibetan verbs is one of the important research topics in Tibetan language processing. In this paper, we propose a Bi-LSTM neural network model for Tibetan verb error correction by analyzing the usage rules of verbs in Tibetan, summarizing the grammatical, semantic and spelling features of verbs, and proposes a Bi-LSTM neural network model for Tibetan verb error correction based on these features, which not only extracts various features of verbs, but also capture the contextual information of verbs through Bi-LSTM neural network. The method proposed in this work solves the drawbacks of the traditional methods of low generalization and inability to obtain long-distance contextual implicit information. The experimental results show that the accuracy, recall and F1 values of the proposed method on the test set reach 97.3%,95.7% and 96.9%, respectively, indicating the effectiveness of the proposed method on the task of automatic error correction for Tibetan verbs.

关键词：

Real-time Depth Estimation for Aerial Panoramas in Virtual Reality

学校读者我要写书评

暂无评论

Real-time Depth Estimation for Aerial Panoramas in Virtual R...

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Di Xu Xiaojun Liu Yanning Zhang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

With the emergence of consumer-level 360° panoramic cameras, omnidirectional RGB images and videos are now easy to be captured either in the hand-held mode or from a drone. Although previous works achieve plausible results in room-sized panoramic datasets, they are limited in indoor scenes with little rotations. In this paper, we present a real-time depth estimation method for more challenging aerial panoramas, where the viewing angle is changing rapidly and the lighting condition is more complicated. Our graph convolutional network(GCN)-based framework makes full use of the global connection information of the omnidirectional images, and is trained with extensive outdoor data. Experiments show that our method is robust to estimate the depth of outdoor aerial panoramas captured from various angles accurately.

关键词： Estimation Videos Distortion Cameras Three-dimensional displays Real-time systems Drones

A novel pixel-based deep neural network in posterior probability space for the detection of agriculture changes using remote sensing data

学校读者我要写书评

暂无评论

Remote Sensing applications: Society and Environment 2025年 38卷

作者： Singh, Gurwinder Vyas, Narayan Dahiya, Neelam Singh, Sartajvir Bhati, Neha Sood, Vishakha Gupta, Dileep Kumar Department of Computer Application Chandigarh School of Business Chandigarh Group of Colleges Jhanjeri Punjab Mohali 140307 India Department Advanced Centre of Research & Innovation Chandigarh Group of Colleges Jhanjeri Punjab Mohali 140307 India Department of Computer Science and Application Vivekananda Global University Rajasthan Jaipur 303012 India Department of Computer Science Punjabi University Punjab Patiala 140307 India Chitkara University Institute of Engineering and Technology Chitkara University Punjab 140401 India University Institute of Engineering Chandigarh University Gharuan Punjab 140413 India Department of Research and Development Flexxited Karnataka Bengaluru 560061 India Department of Civil Engineering Indian Institute of Technology Ropar 140001 India Department of Electronics School of Engineering Galgotias University Greater Noida Gautam Buddh Nagar Uttar Pradesh 203201 India

Agricultural land classification is a crucial and demanding task, essential for managing resources and tracking changes in farming activities. Remote sensing (RS) is an excellent technology for monitoring agricultural land and detecting seasonal fluctuations globally. Deep learning models offer promising prospects for crop monitoring. While traditional machine learning methods struggle to capture temporal variations in agricultural land efficiently. This study addresses the challenge of accurately classifying land cover and detecting year-to-year changes using a deep learning (DL)-based approach. The novelty of this research is an integration using a pixel-based deep neural network (PDNN) classifier, which will advance the classification abilities for identifying land cover classes. By comparing images taken over time, the PDNN can help identify different land cover efficiently. The thematic images using the PDNN were derived, and change detection was carried out by adopting a posterior probability space (PPS)-based change detection. The application of the proposed model is demonstrated using the Landsat-9 dataset over Moga District, Punjab, India. Compared to the random forest (RF) and support vector machine (SVM), the PDNN model achieved great performance. While PDNN had an accuracy ranging from 90.6 % to 93.6 %, RF and SVM had lower accuracies, with RF ranging between 86.8 % and 92.2 % and SVM between 88 % and 92.4 %. The PDNN model also excelled in detecting changes in land cover, showing an accuracy between 87.4 % and 90 %, while RF achieved 82.9 %–86.2 % and SVM ranged from 79 % to 83.9 %. The proposed model was adept at capturing changes in agricultural land cover, such as year-to-year variations. The PDNN model demonstrated superior proficiency in capturing seasonal and year-to-year variations in agricultural land cover, effectively identifying subtle transitions in crop cycles. This highlights its potential for long-term agricultural monitoring and precisio

关键词： Agriculture Change detection Landsat-9 Pixel-based Pixel-based deep neural network (PDNN)