29 Hits in 5.6 sec

The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results

Yan Jia, Xingming Wang, Xiaoyi Qin, Yinping Zhang, Xuyang Wang, Junjie Wang, Dong Zhang, Ming Li
2021 Conference of the International Speech Communication Association  
The 2020 Personalized Voice Trigger Challenge (PVTC2020) addresses two different research problems in a unified setup: joint wake-up word detection with speaker verification on closetalking single microphone  ...  Results show that state-of-the-art personalized voice trigger methods are still based on the two stage design, however, this benchmark database could also be used to evaluate multi-task joint learning  ...  The 2020 Personalized Voice Trigger Challenge (PVTC2020), which aims at providing a common platform for the research community to advance the state-of-the-art techniques in this field.  ... 
doi:10.21437/interspeech.2021-602 dblp:conf/interspeech/JiaWQZWWZL21 fatcat:sas7dskmszdyrgz6kd2htzawwa

Review of the application of intelligent speech technology in education

Jianqing Gao, Genshun Wan, Kui Wu, Zhonghua Fu
2022 Journal of China Computer-Assisted Language Learning  
Moreover, we propose three kinds of challenging problems in the application of intelligent speech technology, including the recognition of domain-related terms, the recognition of code-switching and the  ...  Meanwhile, we also discuss what language teachers and researchers can do in solving the above technical problems.  ...  Along with the appearance of deep belief networks (DBN) in 2006, both opportunities and challenges have emerged for automatic speech recognition systems.  ... 
doi:10.1515/jccall-2022-0004 fatcat:c76t6uj2yvgndoc2qgyfeik6ea

Data Mining on Smartphones: An Introduction and Survey

Darren Yates, Md Zahidul Islam
2022 ACM Computing Surveys  
Data mining is the science of extracting information or 'knowledge' from data. It is a task commonly executed on cloud computing resources, personal computers and laptops.  ...  In this paper, we focus on the intersection of smartphones and data mining.  ...  The motivation for this research is the idea that everyone's mental health triggers can be diferent and the smartphone provides suicient storage and processing speed to create a custom model for each individual  ... 
doi:10.1145/3529753 fatcat:4ntpiqsnufhuhk7toc7fj6gdla

Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning [article]

Chengfei Lv, Chaoyue Niu, Renjie Gu, Xiaotang Jiang, Zhaode Wang, Bin Liu, Ziqi Wu, Qiulin Yao, Congyu Huang, Panos Huang, Tao Huang, Hui Shu (+8 others)
2022 arXiv   pre-print
quickly identifying the best backend with runtime optimization for a computation graph.  ...  To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the  ...  Acknowledgments We sincerely thank our shepherd, Wenjun Hu, for her insightful and thorough guidance. We thank the anonymous OSDI reviewers for their constructive feedback.  ... 
arXiv:2205.14833v1 fatcat:d32fpqs2fvbrperbcqyetmuoaq

Stress Allostasis in Substance Use Disorders: Promise, Progress, and Emerging Priorities in Clinical Research

Gaylen E. Fronk, Sarah J. Sant'Ana, Jesse T. Kaye, John J. Curtin
2020 Annual Review of Clinical Psychology  
Expected final online publication date for the Annual Review of Clinical Psychology, Volume 16 is May 7, 2020. Please see for revised estimates.  ...  Additionally, we examine the field's success to date in targeting stressors and stressor reactivity in treatments for SUDs.  ...  For personal use only.CP16CH13_CurtinARjats.cls Annu. Rev. Clin. Psychol. 2020.16. Downloaded from Access provided by on 05/07/20. For personal use only.  ... 
doi:10.1146/annurev-clinpsy-102419-125016 pmid:32040338 pmcid:PMC7259491 fatcat:v2cbireerre4bcugqcypchcxz4

A Vision for Science Gateways: Bridging the Gap and Broadening the Outreach

Sandra Gesing, Steven Brandt, Shannon Bradley, Mark Potkewitz, Kerk Kee, Noreen Whysel, Mark Perri, Sean Cleveland, Annelie Rugg, Jack Smith
2021 Practice and Experience in Advanced Research Computing  
We explore two particularly promising opportunities for gateways -computational social sciences and virtual reality -and make the case for the gateway community to be more intentional in engaging with  ...  This paper serves as a roadmap for a vision of science gateways in the next ten years.  ...  voice activated elevators and hearing loop systems, for example.  ... 
doi:10.1145/3437359.3465579 fatcat:cawpicidufgzvppu2tcfy2zdty

Deliverable D3.7 Consolidated Projects Summary Report

Alasdair Reid, Matias Barberis Rami
2021 Zenodo  
This report is part of a project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No.825618  ...  Furthermore, it will describe how the calls were thematically organised and how the projects advanced in the state-of-the-art of the proposed themes as well as in maturity level.  ...  The baseline system is to be engineered and designed abiding to the principles of privacy by design. During the TRUSTRULES project, research was performed aiming to evaluate the possible  ... 
doi:10.5281/zenodo.5767430 fatcat:w2lxzgxktretjcv7h4xotz7xaq

Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning

Lyes Khacef, Laurent Rodriguez, Benoît Miramond
2020 Electronics  
We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task.  ...  The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system.  ...  The authors would like to acknowledge the 2019 Capocaccia Neuromorphic Workshop and all its participants for the fruitful discussions.  ... 
doi:10.3390/electronics9101605 fatcat:qts5ztll7bck5hobmazoda42me

Brain-inspired self-organization with cellular neuromorphic computing for multimodal unsupervised learning [article]

Lyes Khacef, Laurent Rodriguez, Benoit Miramond
2020 arXiv   pre-print
We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task.  ...  The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system.  ...  For example, when someone talks to us in person, we simultaneously hear the speakers voice and see the speakers lips move.  ... 
arXiv:2004.05488v3 fatcat:sl4ulteumfhjpc5m7s4lvqdkbi

Trustworthy AI: A Computational Perspective [article]

Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang
2021 arXiv   pre-print
For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.  ...  We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.  ...  Voice recognition systems show gender bias by processing the voices of men and women differently [168] .  ... 
arXiv:2107.06641v3 fatcat:ymqaxvzsoncqrcosj5mxcvgsuy

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies  ...  Besides, NPU is a specialized circuit that can be used to execute deep learning applications, as NPU is an option of GPU for deep learning training but runs much faster than the GPU. Berggren et al.  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

D1.1 - State of the Art Analysis

Danilo Ardagna
2021 Zenodo  
In the last part of the deliverable, we report an overview of the performance modelling solutions, security, and privacy problems for AI applications in edge environments.  ...  It examines the standardisation and opensource landscape, where many of the emerging standards are mainly focused on the network layer, also highlighting opportunities for open-source community involvement  ...  Nowadays, users' personal, extremely sensitive data like photos and voice recordings are kept indefinitely by the companies that collect them.  ... 
doi:10.5281/zenodo.6372377 fatcat:f6ldfuwivbcltew4smiiwphfty

Enabling Multi-Functional 5G and Beyond User Equipment: A Survey and Tutorial

Yiming Huo, Xiaodai Dong, Wei Xu, Marvin Yuen
2019 IEEE Access  
design, followed by an investigation of state-of-the-art hardware development from the systems and circuits standpoint.  ...  Finally, the new trends of UE design and terahertz technologies for 5G and beyond applications are investigated and envisioned. 116976 VOLUME 7, 2019 Y.  ...  ACKNOWLEDGEMENT The authors would like to acknowledge Natural Sciences and Engineering Research Council of Canada, National Natural Science Foundation of China for the support of this project, and valuable  ... 
doi:10.1109/access.2019.2936291 fatcat:wxssot7455etxmxnokgsdkobbu

Intelligent Edge-Embedded Technologies for Digitising Industry [chapter]

Ovidiu Vermesan, Mario Diaz Nava
2022 Intelligent Edge-Embedded Technologies for Digitising Industry  
Also covered are developments stemming from new market demands in systems, products, and technologies such as personal communications services, multimedia systems, enterprise networks, and optical communications  ...  The "River Publishers Series in Communications and Networking" is a series of comprehensive academic and professional books which focus on communication and network systems.  ...  Acknowledgements This work is conducted under the framework of the ECSEL AI4DI "Artificial Intelligence for Digitising Industry" project.  ... 
doi:10.13052/rp-9788770226103 fatcat:mgz277pmkbetvbpoaomoktzgzi

Current Industry 4.0 Platforms – An Overview

Sauer Christian, Eichelberger Holger, Ahmadian Amir Shayan, Dewes Andreas, Jürjens Jan
2021 Zenodo  
Based on the cross-platform analysis of the 16 topic areas, we derive challenges for future platforms and especially for our work in IIP-Ecosphere.  ...  The document describes the approach to data collection, the detailed results for individual industrial platforms, and a summarizing overview.  ...  Data collection for both phases took place in the period from June 2020 to August 2020.  ... 
doi:10.5281/zenodo.4485756 fatcat:f4m2swkalnh3biy5vjypsix32y
« Previous Showing results 1 — 15 out of 29 results