检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Leying Zhang, Wangyou Chen, Zhengyang Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containing backgrounds. To address these challenges, we propose a Controllable Masked Speech Prediction strategy coupled with a dual-speaker encoder, utilizing a task-related control signal to guide the prediction of dual background removal and preservation targets. Experimental results demonstrate that our approach enables precise control over the removal or preservation of background across various acoustic conditions and exhibits strong generalization capabilities in unseen scenarios. © 2025, CC BY.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Sensor Fusion for Learning Rich Models for Interacting Soft Robots

Multi-modal Sensor Fusion for Learning Rich Models for Inter...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Thomas George Thuruthel Fumiya Iida Department of Engineering The Bio-Inspired Robotics Lab University of Cambridge UK Department of Computer Science University College London London UK

Soft robots are typically approximated as low-dimensional systems, especially when learning-based methods are used. This leads to models that are limited in their capability to predict the large number of deformation modes and interactions that a soft robot can have. In this work, we present a deep-learning methodology to learn high-dimensional visual models of a soft robot combining multimodal sensorimotor information. The models are learned in an end-to-end fashion, thereby requiring no intermediate sensor processing or grounding of data. The capabilities and advantages of such a modelling approach are shown on a soft anthropomorphic finger with embedded soft sensors. We also show that how such an approach can be extended to develop higher level cognitive functions like identification of the self and the external environment and acquiring object manipulation skills. This work is a step towards the integration of soft robotics and developmental robotics architectures to create the next generation of intelligent soft robots.

关键词： Visualization Shape control Soft sensors Tactile sensors Soft robotics Predictive models Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

FusionPortableV2: A Unified Multi-Sensor Dataset for Generalized SLAM Across Diverse Platforms and Scalable Environments

arXiv

引用

arXiv 2024年

作者： Wei, Hexiang Jiao, Jianhao Hu, Xiangcheng Yu, Jingwen Xie, Xupeng Wu, Jin Zhu, Yilong Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Robot Perception and Learning Lab Department of Computer Science University College London United Kingdom Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangzhou China

Simultaneous Localization and Mapping (SLAM) technology has been widely applied in various robotic scenarios, from rescue operations to autonomous driving. However, the generalization of SLAM algorithms remains a significant challenge, as current datasets often lack scalability in terms of platforms and environments. To address this limitation, we present FusionPortableV2, a multi-sensor SLAM dataset featuring sensor diversity, varied motion patterns, and a wide range of environmental scenarios. Our dataset comprises 27 sequences, spanning over 2.5 hours and collected from four distinct platforms: a handheld suite, a legged robot, a unmanned ground vehicle (UGV), and a vehicle. These sequences cover diverse settings, including buildings, campuses, and urban areas, with a total length of 38.7km. Additionally, the dataset includes ground-truth (GT) trajectories and RGB point cloud maps covering approximately 0.3km2. To validate the utility of our dataset in advancing SLAM research, we assess several state-of-the-art (SOTA) SLAM algorithms. Furthermore, we demonstrate the dataset's broad application beyond traditional SLAM tasks by investigating its potential for monocular depth estimation. The completae dataset, including sensor data, GT, and calibration details, is accessible at https://***/dataset/fusionportable v2. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Exploring Automated Feature Engineering for Energy Consumption Forecasting with AutoML

Exploring Automated Feature Engineering for Energy Consumpti...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Nasser Alkhulaifi Alexander L. Bowler Direnc Pekaslan Isaac Triguero Nicholas J. Watson Computational Optimisation and Learning (COL) Lab School of Computer Science University of Nottingham Nottingham UK Faculty of Environment School of Food Science and Nutrition University of Leeds Leeds UK Lab for Uncertainty in Data and Decision Making (LUCID) School of Computer Science University of Nottingham Nottingham UK Department of Computer Science and Artificial Intelligence University of Granada Spain DaSCI Andalusian Institute in Data Science and Computational Intelligence Granada Spain

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Machine learning methods are widely used to predict energy consumption, aiming to enhance efficiency and support environmental goals. However, developing these models is traditionally time-consuming and expert-dependent. While Automated Machine Learning (AutoML) has emerged as a valuable approach to streamlining machine learning pipelines, including appropriate preprocessing and learning algorithms, it may still require human experts. These experts might be needed to generate new, interpretable features that could significantly improve model performance. This is particularly relevant in complex settings such as the energy domain, where deep learning's automatic feature extraction lacks interpretability. To address this challenge, this exploratory work introduces an automated feature engineering method tailored for energy forecasting problems. It involves generating a comprehensive set of features that can be fed into AutoML, thereby reducing the need for domain knowledge in feature engineering. The proposed method has been validated using eleven datasets from various energy domains, including residential buildings, renewable energy, and regional energy consumption, with state-of-the-art AutoML methods, namely H20, TPOT, AutoGluon, and FLAML. The results demonstrate a noticeable reduction in prediction errors across all the examined datasets.

关键词： Knowledge engineering Deep learning Energy consumption Renewable energy sources Machine learning algorithms Pipelines Automated machine learning Prediction algorithms Feature extraction Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detecting Ballistic Motions in Quadruped Robots: A Boosted Tree Motif Classifier for Understanding Reinforcement Learning

Detecting Ballistic Motions in Quadruped Robots: A Boosted T...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Christopher Allred Jason Pusey Mario Harper Department of Computer Science Utah State University (USU) Computational & Information Sciences Directorate at Army Research Lab (ARL)

Quadrupedal robots require sophisticated algorithms to learn dynamic and ballistic motions, such as jumping. Traditional methods, which often employ Reinforcement Learning (RL), face inherent limitations in identifying the formation of desired actions during training. This study introduces the Boosted Tree Motif Classifier (BTMC), a novel approach designed to accurately detect complex motion patterns, thus facilitating learning dynamic actions in quadrupedal robots. Unlike classical motif search techniques and simple neural networks, which achieved a precision rate of merely 2% and 12%, respectively, in identifying a ”jump” motif, BTMC demonstrated remarkable efficiency with a 96% precision rate. The overall accuracy of BTMC was comparable to other learning approaches developed but superior in capturing essential motifs crucial for dynamic motions. The results highlight BTMC's potential as an innovative solution in RL-based robotic systems, offering an advancement in robotic locomotion. Our findings open up new avenues for RL's theoretical and practical applications in robotics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generation-Based Target Speech Extraction with Speech Discretization and Vocoder

Generation-Based Target Speech Extraction with Speech Discre...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Linfeng Yu Wangyou Zhang Chenpeng Du Leying Zhang Zheng Liang Yanmin Qian AI Institute Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China

Target speech extraction (TSE) is a task aiming at isolating the speech of a specific target speaker from an audio mixture, with the help of an auxiliary recording of that target speaker. Most existing TSE methods employ discrimination-based models to estimate the target speaker’s proportion in the mixture, but they often fail to compensate for the missing or highly corrupted frequency components in the speech signal. In contrast, the generation-based methods can naturally handle such scenarios via speech resynthesis. In this paper, we propose a novel discrete token based TSE approach by combining state-of-the-art speech discretization and vocoder techniques. By predicting a sequence of discrete tokens with the auxiliary audio and employing a vocoder that takes discrete tokens as input, the target speech can be effectively re-synthesized while eliminating interference. Our experiments conducted on the WSJ0-2mix and Libri2mix datasets demonstrate that our proposed method yields high-quality target speech without interference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition

DQ-Whisper: Joint Distillation and Quantization for Efficien...

引用

IEEE Spoken Language Technology Workshop

作者： Hang Shao Bei Liu Wei Wang Xun Gong Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

As a popular multilingual and multitask pre-trained speech model, Whisper has the problem of curse of multilinguality. To enhance multilingual capabilities in small Whisper models, we propose DQ-Whisper, a novel joint distillation and quantization framework to compress Whisper for efficient inference. Firstly, we propose a novel dynamic matching distillation strategy. Then, a quantization-aware distillation framework is introduced to integrate quantization with distillation. Experimental results on various multilingual datasets show that our suggested distillation approach can effectively enhance the multilingual capabilities of small Whisper models without increasing computational costs. Up to 5.18x reduction in model size is achieved with marginal performance degradation. In addition, quantization is compatible with distillation, which can result in a higher compression rate.

关键词： Degradation Quantization (signal) computational modeling Conferences Merging Speech recognition Multilingual computational efficiency

来源：评论

学校读者我要写书评

暂无评论

ASFM: Augmented Social Force Model for Legged Robot Social Navigation

ASFM: Augmented Social Force Model for Legged Robot Social N...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Sebastian Ægidius Rodrigo Chacón-Quesada Andromachi Maria Delfaki Dimitrios Kanoulas Yiannis Demiris Department of Computer Science Robot Perception and Learning Lab University College London Gower Street London UK Department of Electrical and Electronic Engineering Personal Robotics Lab Imperial College London London UK Department of Computer Science AI Centre UCL and the Archimedes/Athena RC Greece

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

Social navigation in robotics primarily involves guiding mobile robots through human-populated areas, with pedestrian comfort balanced with efficient path-finding. Although progress has been seen in this field, a solution for the seamless integration of robots into pedestrian settings remains elusive. In this paper, a social force model for legged robots is developed, utilizing visual perception for human localization. In particular, an augmented social force model is introduced, incorporating refined interpretations of repulsive forces and avoidance behaviors based on pedestrian actions, alongside a target following mechanism. Experimental evaluation on a quadruped robot, through various scenarios, including interactions with oncoming pedestrians, crowds, and obstructed paths, demonstrates that the proposed augmented model significantly improves upon previous baseline methods in terms of chosen path length, average velocity, and time-to-goal for effective and efficient social navigation. The code isopen-source, while video demonstrations can be found on the project’s webpage: https://***/ASFM/

关键词： Legged locomotion Location awareness Pedestrians Codes Navigation Force Humanoid robots Quadrupedal robots Visual perception

来源：评论

学校读者我要写书评

暂无评论

AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation

arXiv

引用

arXiv 2025年

作者： Kienle, Claudius Alt, Benjamin Schneider, Finn Pertlwieser, Tobias Jäkel, Rainer Rayyes, Rania ArtiMinds Robotics Karlsruhe Germany IAS Lab Computer Science Department TU Darmstadt Germany AICOR Institute for Artificial Intelligence University of Bremen Germany Karlsruhe Germany

Despite the widespread adoption of industrial robots in automotive assembly, wire harness installation remains a largely manual process, as it requires precise and flexible manipulation. To address this challenge, we design a novel AI-based framework that automates cable connector mating by integrating force control with deep visuotactile learning. Our system optimizes search-and-insertion strategies using first-order optimization over a multimodal transformer architecture trained on visual, tactile, and proprioceptive data. Additionally, we design a novel automated data collection and optimization pipeline that minimizes the need for machine learning expertise. The framework optimizes robot programs that run natively on standard industrial controllers, permitting human experts to audit and certify them. Experimental validations on a center console assembly task demonstrate significant improvements in cycle times and robustness compared to conventional robot programming approaches. Videos are available under https: //***/*** Codes 68T40 © 2025, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Approximate Analytic and Neural Network Solutions for Effective Mass Schrodinger Equation With Yukawa's Potential 2

A Comparison of Approximate Analytic and Neural Network Solu...

引用

2nd IEEE International Conference on Artificial Intelligence in Everything, AIE 2022

作者： Fotso Kamsu, Brigitte Vubangsi, Mercel Tchoffo, M. Al-Turjman, Fadi University of Dschang Condensed Matter Electronics and Signal Processing Research Unit Department of Physics Faculty of Science Cameroon Near East University Ai and Robotics Institute Artificial Intelligence Engineering Dept. Nicosia Turkey University of Bamenda Nwr Computational Materials Science Lab Department of Computer Science Htttc Bambili Cameroon University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Cyprus

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

We model a compositionally graded heterostructure using the effective mass approach with a screened Coulomb potential. Approximate analytical solutions to the model are compared with a Neural Network output and good agreement is achieved, paving the way for Artificial Intelligence modeling of systems with graded composition. © 2022 IEEE.

关键词： Grading

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：