检索结果-内蒙古大学图书馆

Wekws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit

学校读者我要写书评

暂无评论

Wekws: A Production First Small-Footprint End-to-End Keyword...

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

作者： Jie Wang Menglong Xu Jingyong Hou Binbin Zhang Xiao-Lei Zhang Lei Xie Fuping Pan School of Marine Science and Technology Northwestern Polytechnical University Xi’an China WeNet Open Source Community Horizon Robotics Beijing China Audio Speech and Language Processing Group (ASLP@NPU) School of Computer Science Northwestern Polytechnical University Xi’an China

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have be-come the most popular approach for on-device KWS tasks. However, there is still a gap between the research and deployment of E2E KWS methods. In this paper, we introduce WeKws, a production-quality, easy-to-build, and convenient-to-be-applied E2E KWS toolkit. WeKws contains the implementations of several state-of-the-art backbone networks, making it achieve highly competitive results on three publicly available datasets. To make WeKws a pure E2E toolkit, we utilize a refined max-pooling loss to make the model learn the ending position of the keyword by itself, which significantly simplifies the training pipeline and makes WeKws very efficient to be applied in real-world scenarios. The toolkit is publicly available at https://***/wenet-e2e/wekws.

关键词： Training Pipelines Production Signal processing Benchmark testing Acoustics Task analysis

Multimodal Surface Sensing based on Hybrid Flexible Triboelectric and Piezoresistive Sensor

学校读者我要写书评

暂无评论

Multimodal Surface Sensing based on Hybrid Flexible Triboele...

2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022

作者： Lin, Zenan Lei, Kai Chong Mu, Shilong Song, Ziwu Dai, Yuan Ding, Wenbo Zhang, Xiao-Ping Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University China Tencent Robotics X Lab China Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University RISC-V International Open Source Laboratory China Shenzhen International Graduate School Tsinghua University Department of Electrical Computer and Biomedical Engineering Ryerson University China

ISBN: (纸本)9781450394239

Sensing the surface properties through touch, as the most natural perceptual way of humans, has become an important and practical method for human-machine interactions (HMI) and robot manipulations. In this paper, we design a fingertip hybrid flexible tactile sensor for multimodal surface sensing, based on the triboelectric and piezoresistive mechanisms. A real-time tactile sensing system is implemented on a 3D-printed robot finger together with a wireless data acquisition board. A virtual data generation method is proposed to expand the model adaptability under different compression force levels. Moreover, considering the characteristics of data generated by our sensors, a novel deep learning model with a residual structure is developed, named parallel residual convolutional neural network (PR-CNN). Our model outperforms the state-of-the-art models, i.e., Res-CNN, LSTM-FCN and InceptionTime, with over 96% accuracy, on three classification tasks, including textures (13 types), materials (10 types), and combinations of textures and materials (18 types). The proposed system has broad applications in service robots, industrial sorting robots, and HMI. © 2022 Owner/Author.

关键词： Textures

STEV: Stretchable Triboelectric E-skin enabled Proprioceptive Vibration Sensing for Soft Robot

学校读者我要写书评

暂无评论

STEV: Stretchable Triboelectric E-skin enabled Proprioceptiv...

IEEE International Conference on robotics and Automation (ICRA)

作者： Zihan Wang Kai-Chong Lei Huaze Tang Shoujie Li Yuan Dai Wenbo Ding Xiao-Ping Zhang Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University China Tencent Robotics X Lab Shenzhen China RISC-V International Open Source Laboratory Shenzhen China Department of Electrical Computer and Biomedical Engineering Ryerson University Toronto ON Canada

Vibration perception is essential for robotic sensing and dynamic control. Nevertheless, due to the rigorous demand for sensor conformability and stretchability, enabling soft robots with proprioceptive vibration sensing remains challenging. This paper proposes a novel liquid metal-based stretchable e-skin via a kirigami-inspired design to enable soft robot proprioceptive vibration sensing. The e-skin is fabricated into 0.1mm ultrathin thickness, ensuring its negligible influence on the overall stiffness of the soft robot. Moreover, the working mechanism of the e-skin is based on the ubiquitous triboelectrification effect, which transduces mechanical stimuli without external power supply. To demonstrate the practicability of the e-skin, we built a soft gripper consisting of three soft robotic fingers with proprioceptive vibration sensing. Our experiment shows that the gripper can accurately distinguish the grain category (six grains with the same mass, 99.9% accuracy) and the packaging quality (100% accuracy) by simply shaking the gripped bottle. In summary, a soft robotic proprioceptive vibration sensing solution is proposed; it helps soft robots to have a more comprehensive awareness of their self-state and may inspire further research on soft robotics.

关键词：

WEKWS: A PRODUCTION FIRST SMALL-FOOTPRINT END-TO-END KEYWORD SPOTTING TOOLKIT

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jie Xu, Menglong Hou, Jingyong Zhang, Binbin Zhang, Xiao-Lei Xie, Lei Pan, Fuping School of Marine Science and Technology Northwestern Polytechnical University Xi'An China School of Computer Science Northwestern Polytechnical University Xi'An China Horizon Robotics Beijing China WeNet Open Source Community China

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have become the most popular approach for on-device KWS tasks. However, there is still a gap between the research and deployment of E2E KWS methods. In this paper, we introduce WeKws, a production-quality, easy-to-build, and convenient-to-be-applied E2E KWS toolkit. WeKws contains the implementations of several state-of-the-art backbone networks, making it achieve highly competitive results on three publicly available datasets. To make WeKws a pure E2E toolkit, we utilize a refined max-pooling loss to make the model learn the ending position of the keyword by itself, which significantly simplifies the training pipeline and makes WeKws very efficient to be applied in real-world scenarios. The toolkit is publicly available at https://***/wenet-e2e/wekws. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Path Generation for Wheeled Robots Autonomous Navigation on Vegetated Terrain

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jian, Zhuozhu Liu, Zejia Shao, Haoyu Wang, Xueqian Chen, Xinlei Liang, Bin The Center for Artificial Intelligence and Robotics Shenzhen International Graduate School Tsinghua University Shenzhen518055 China The School of Mechanical Engineering and Automation at Harbin Institute of Technology Shenzhen518055 China The Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Pengcheng Lab Shenzhen518055 China RISC-V International Open Source Laboratory Shenzhen518055 China

Wheeled robot navigation has been widely used in urban environments, but navigation in wild vegetation is still challenging. External sensors (LiDAR, camera etc.) are often used to construct point cloud map of the surrounding environment, however, the supporting rigid ground used for travelling cannot be detected due to the occlusion of vegetation. This often leads to unsafe or non-smooth paths during the planning process. To address the drawback, we propose the PE-RRT* algorithm, which effectively combines a novel support plane estimation method and sampling algorithm to generate real-time feasible and safe path in vegetation environments. In order to accurately estimate the support plane, we combine external perception and proprioception, and use Multivariate Gaussian Processe Regression (MV-GPR) to estimate the terrain at the sampling nodes. We build a physical experimental platform and conduct experiments in different outdoor environments. Experimental results show that our method has high safety, robustness and generalization. The source code is released for the reference of the community. Copyright © 2023, The Authors. All rights reserved.

关键词： Vegetation

Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit

学校读者我要写书评

暂无评论

Wespeaker: A Research and Production Oriented Speaker Embedd...

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

作者： Hongji Wang Chengdong Liang Shuai Wang Zhengyang Chen Binbin Zhang Xu Xiang Yanlei Deng Yanmin Qian CSE Dept MoE Key Lab of AI X-LANCE Lab Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China WeNet Open Source Community School of Marine Science and Technology Northwestern Polytechnical University Xi’an China NVIDIA Santa Clara USA Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Horizon Robotics Beijing China AISpeech Ltd Suzhou China

关键词： Codes Production Signal processing Data models Acoustics Speaker recognition Task analysis

WESPEAKER: A RESEARCH AND PRODUCTION ORIENTED SPEAKER EMBEDDING LEARNING TOOLKIT

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Hongji Liang, Chengdong Wang, Shuai Chen, Zhengyang Zhang, Binbin Xiang, Xu Deng, Yanlei Qian, Yanmin X-LANCE Lab Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China School of Marine Science and Technology Northwestern Polytechnical University Xi'An China Horizon Robotics Beijing China AISpeech Ltd Suzhou China NVIDIA Santa Clara United States WeNet Open Source Community China

关键词： Embeddings

When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Shoujie Wang, Zihan Wu, Changsheng Li, Xiang Luo, Shan Fang, Bin Sun, Fuchun Zhang, Xiao-Ping Ding, Wenbo Tsinghua Shenzhen International Graduate School Shenzhen518055 China RISC-V International Open Source Laboratory Shenzhen518055 China Department of Materials Science and Engineering National University of Singapore Singapore117575 Singapore Centre for Robotics Research King’s College London LondonWC2R 2LS United Kingdom Department of Automation Tsinghua University Beijing100084 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

Tactile sensors, which provide information about the physical properties of objects, are an essential component of robotic systems. The visuotactile sensing technology with the merits of high resolution and low cost has facilitated the development of robotics from environment exploration to dexterous operation. Over the years, several reviews on visuotactile sensors for robots have been presented, but few of them discussed the significance of signal processing methods to visuotactile sensors. Apart from ingenious hardware design, the full potential of the sensory system toward designated tasks can only be released with the appropriate signal processing methods. Therefore, this paper provides a comprehensive review of visuotactile sensors from the perspective of signal processing methods and outlooks possible future research directions for visuotactile sensors. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal processing

A Platypus-Inspired Electro-Mechanosensory Finger for Remote Control and Tactile Sensing

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Ding, Wenbo Mu, Shilong Li, Shoujie Zhao, Hongfa Wang, Zihan Xiao, Xiao Lin, Zennan Song, Ziwu Tang, Huaze Xu, Qinghao Wang, Dongkai Lee, Wang Wei Wu, Changsheng Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Department of Bioengineering China Institute for Health Innovation and Technology National University of Singapore Singapore117599 Singapore SIA-NUS Digital Aviation Corporate Lab National University of Singapore Singapore117602 Singapore Tencent Robotics X Shenzhen518054 China Department of Materials Science and Engineering National University of Singapore Singapore117575 Singapore RISC-V International Open Source Laboratory Shenzhen518055 China

Advancement in human-robot interaction (HRI) is essential for the development of intelligent robots, but there lack paradigms to integrate remote control and tactile sensing for an ideal HRI. In this study, inspired by the platypus beak sense, we propose a bionic electro-mechanosensory finger (EM-Finger) synergizing triboelectric and visuotactile sensing for remote control and tactile perception. A triboelectric sensor array made of a patterned liquid-metal-polymer conductive (LMPC) layer encodes both touchless and tactile interactions with external objects into voltage signals in the air, and responds to electrical stimuli underwater for amphibious wireless communication. Besides, a three-dimensional finger-shaped visuotactile sensing system with the same LMPC layer as a reflector measures contact-induced deformation through marker detection and tracking methods. A bioinspired bimodal deep learning algorithm implements data fusion of triboelectric and visuotactile signals and achieves the classification of 18 common material types under varying contact forces with an accuracy of 94.4%. The amphibious wireless communication capability of the triboelectric sensor array enables touchless HRI in the air and underwater, even in the presence of obstacles, while the whole system realizes high-resolution tactile sensing. By naturally integrating remote contorl and tactile sensing, the proposed EM-Finger could pave the way for enhanced HRI in machine intelligence. © 2023, The Authors. All rights reserved.

关键词： Human robot interaction