检索结果-内蒙古大学图书馆

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Mann, Daniel Raissi, Tina Michel, Wilfried Schluter, Ralf Ney, Hermann AppTek GmbH Aachen52062 Germany Rwth Aachen University Machine Learning and Human Language Technology Computer Science Department Aachen52074 Germany

ISBN: (纸本)9798350306897

We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration *** implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition *** investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings. © 2023 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Investigating The Effect of Language Models in Sequence Discriminative Training For Neural Transducers

Investigating The Effect of Language Models in Sequence Disc...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Yang, Zijian Zhou, Wei Schluter, Ralf Ney, Hermann Rwth Aachen University Machine Learning and Human Language Technology Computer Science Department Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9798350306897

In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and N-best-list approaches are examined. For lattice-free methods with phoneme-level LMs, we propose a method to approximate the context history to employ LMs with full-context dependency. This approximation can be extended to arbitrary context length and enables the usage of word-level LMs in lattice-free methods. Moreover, a systematic comparison is conducted across lattice-free and N-best-list-based methods. Experimental results on Librispeech show that using the word-level LM in training outperforms the phoneme-level LM. Besides, we find that the context size of the LM used for probability computation has a limited effect on performance. Moreover, our results reveal the pivotal importance of the hypothesis space quality in sequence discriminative training. © 2023 IEEE.

关键词： Transducers

来源：评论

学校读者我要写书评

暂无评论

NBNLP-A Naïve Bayes-Natural language Processing algorithm for Chatbots 4

NBNLP-A Naïve Bayes-Natural language Processing algorithm f...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bahheti, Mamta Patra, Indrajit Sarkar, Paramita Sharma, Amit Mandal, Pawan Santhi, M.V.B.T. Hislop College Department of Computer Science Maharashtra Nagpur440001 India Mediterranea University of Reggio Calabria Mediterranea International Centre for Human Rights Research Italy Jis University Department of C.S.E Kolkata India Lkctc Jalandhar India Rimt University Department of Forensic Science Mandi Gobindgarh India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798331518981

In the contemporary era, a growing number of individuals engage with Information and Communication Technology (ICT) tools, witnessing the continuous expansion of technology and its diverse applications. A prevalent observation is the prevalence of virtual machines on websites, adept at responding to user queries and furnishing relevant information - these virtual entities are commonly known as Chatbots. Creating Chatbots involves leveraging a variety of programming languages, such as HTML, CSS, JavaScript, Pluto, PHP, Python, as well as incorporating elements of artificial intelligence and machine learning. Each language contributes unique features to Chatbot's functionality. This work proposes "NBNLP-A Naïve Bayes-Natural language processing algorithm for Chatbots"and provides a straightforward comparison of Chatbots developed in different programming languages, shedding light on their distinct attributes. The ensuing discussion delves into a comparative analysis of the working mechanisms and features inherent in Chatbots crafted using diverse programming languages. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Measuring Social Solidarity During Crisis:The Role of Design Choices

引用

Journal of Social Computing 2022年第2期3卷 139-157页

作者： Steffen Eger Dan Liu Daniela Grunow the Center for Cognitive Interaction Technology(CITEC) Bielefeld UniversityBielefeld 33615Germany the Computer Science Department Technical University DarmstadtDarmstadt 64289Germany the Faculty of Social Sciences Goethe University FrankfurtFrankfurt 60629Germany

Building on our previous work,we assess how social solidarity towards migrants and refugees has changed before and after the onset of the COVID-19 pandemic,by collecting and analyzing a large,novel,and longitudinal dataset of migration-related *** this end,we first annotate above 2000 tweets for(anti-)solidarity expressions towards immigrants,utilizing two annotation approaches(experts ***).On these annotations,we train a BERT model with multiple data augmentation strategies,which performs close to the human upper *** use this high-quality model to automatically label over 240000 tweets between September 2019 and June *** then assess the automatically labeled data for how statements related to migrant(anti-)solidarity developed over time,before and during the COVID-19 *** findings show that migrant solidarity became increasingly salient and contested during the early stages of the pandemic but declined in importance since late 2020,with tweet numbers falling slightly below pre-pandemic levels in summer *** the same period,the share of anti-solidarity tweets increased in a sub-sample of COVID-19-related *** findings highlight the importance of long-term observation,pre-and post-crisis comparison,and sampling in research interested in crisis related *** one of our main contributions,we outline potential pitfalls of an analysis of social solidarity trends:for example,the ratio of solidarity and anti-solidarity statements depends on the sampling design,i.e.,tweet language,Twitter-user accounts’national identification(country known or unknown)and selection of relevant *** our sample,the share of anti-solidarity tweets is higher in native(German)language tweets and among“anonymous”Twitter users writing in German compared to English-language tweets of users located in Germany.

关键词： social solidarity crises COVID-19 natural language processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing and Adversarial: Improve ASR with Speaker Labels 48

Enhancing and Adversarial: Improve ASR with Speaker Labels

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhou, Wei Wu, Haotian Xu, Jingjing Zeineldeen, Mohammad Luscher, Christoph Schluter, Ralf Ney, Hermann Rwth Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9781728163277

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7% relative improvement on the Switchboard Hub5'00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN. © 2023 IEEE.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

The Importance of Performance Feedback in Virtual Reality (VR) Training: A Table Tennis Coach Perspective

The Importance of Performance Feedback in Virtual Reality (V...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Sunday, Kissinger Anvari, Soraya S. Li, Yiwei Sun, Junwei Wehbe, Rina R. Neyedli, Heather Batmaz, Anil Ufuk Machuca, Mayra Donaji Barrera Faculty of Computer Science VR Lab. Dalhousie University HalifaxNS Canada HCI4Good Dalhousie University HalifaxNS Canada University of Western Ontario TorontoON Canada School of Interactive Arts and Technology Simon Fraser University VancouverBC Canada HCI4Good Faculty of Computer Science Dalhousie University HalifaxNS Canada School Health & Human Performance Dalhousie University HalifaxNS Canada Department of Computer Science & Software Engineering Concordia University MontrealQC Canada Faculty of Computer Science Dalhousie University HalifaxNS Canada

ISBN: (纸本)9798400713958

Advances in Virtual Reality (VR) technology have redefined sports training, offering a new modality for athletes to prepare for competitions. This paper explores the coaching strategies used to train novice table tennis players in VR. Through interviews with the coach and participant feedback, we identified key strategies such as personalized feedback, table division, and a structured training regimen for skill development in VR. Challenges include limited facial awareness and the absence of virtual cheering, which impacted the coach’s ability to engage fully with participants. These findings offer valuable insights into coaching strategies in VR environments, contributing to developing more effective and engaging VR training systems. © 2025 Copyright held by the owner/author(s).

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

A Partial Face Encryption in Real World Experiences Based on Features Extraction from Edge Detection

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第7期17卷 69-81页

作者： Azeez, Raghad Abdulaali Jamil, Abeer Salim Mahdi, Mohammed Salih Collage of Education Ibn-Rushed for Human Science University of Baghdad Baghdad Iraq Department of Computer Technology Engineering Al-Mansour University College Baghdad Iraq Business Information College University of Information Technology and Communications Baghdad Iraq

User confidentiality protection is concerning a topic in control and monitoring spaces. In image, user's faces security in concerning with compound information, abused situations, participation on global transmission media and real-world experiences are extremely significant. For minifying the counting needs for vast size of image info and for minifying the size of time needful for the image to be address computationally. consequently, partial encryption userface is picked. This study focuses on a large technique that is designed to encrypt the user's face slightly. Primarily, dlib is utilizing for user-face detection. Susan is one of the top edge detectors with valuable localization characteristics marked edges, is used to extract features vectors from user faces. Moreover, the relevance of the suggested generating key is led to a crucial role in security improvement by producing them as difficult to intruders. According to PSNR values, the recommended encryption algorithms provided an adequate outcome in the encryption, they had a lower encrypting duration and a larger encrypting impact. © 2023,International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Elevating AI Research at Cognitive Agents and interaction Lab: A Technical Report on High-Performance Computing Infrastructure

TechRxiv

引用

TechRxiv 2023年

作者： Khan, Md Mosaddek Cognitive Agents and Interaction Lab Department of Computer Science and Engineering University of Dhaka Bangladesh

The Cognitive Agents and interaction Lab (CAIL) at the University of Dhaka has strategically developed a focused High-Performance Computing (HPC) facility, underpinning its niche in artificial intelligence (AI) research, with a special emphasis — but not limited to — deep and reinforcement learning within the context of multi-agent systems. This technical report outlines the HPC resources at CAIL, highlighting a number of advanced GPUs that drive our research forward. The facility, supported by multiple grants, exemplifies a model for small-scale, high-impact computational research environments. We detail how these resources empower our team to achieve significant strides in AI, despite the challenges of scale, and set a precedent for innovation in the field. © 2023, CC BY.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Relectrode: A reconfigurable electrode for multi-purpose sensing based on microfluidics 21

Relectrode: A reconfigurable electrode for multi-purpose sen...

引用

2021 CHI Conference on human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021

作者： Sun, Wei Chen, Yanjun Zhan, Simon Han, Teng State Key Laboratory of Computer Science Beijing Key Lab of Human-Computer Interaction Institute of SoftwareChinese Academy of Sciences Beijing China

ISBN: (纸本)9781450380966

In this paper, we propose a reconfgurable electrode, RElectrode, using a microfuidic technique that can change the geometry and material properties of the electrode to satisfy the needs for sensing a variety of diferent types of user input through touch/touchless gestures, pressure, temperature, and distinguish between diferent types of objects or liquids. Unlike the existing approaches, which depend on the specifc-shaped electrode for particular sensing (e.g., coil for inductive sensing), RElectrode enables capacity, inductance, resistance/pressure, temperature, pH sensings all in a single package. We demonstrate the design and fabrication of the microfuidic structure of our RElectrode, evaluate its sensing performance through several studies, and provide some unique applications. RElectrode demonstrates technical feasibility and application values of integrating physical and biochemical properties of microfuidics into novel sensing interfaces. © 2021 ACM.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Could human Gaze Augment Detectors of Synthetic Images? 24

Could Human Gaze Augment Detectors of Synthetic Images?

引用

24th International Conference on Digital Signal Processing, DSP 2023

作者： Fotopoulos, Nikolaos Riedmiller, Clara Bozkir, Efe Tsinganos, Panagiotis Ampeliotis, Dimitris Kasneci, Gjergji Kasneci, Enkelejda Skodras, Athanassios Department of Electrical and Computer Engineering University of Patras Greece Department of Computer Science Eberhard Karls University of Tübingen Germany Department of Digital Media and Communication Ionian University Greece Human-Centered Technologies for Learning Technical University of Munich Germany Responsible Data Science Technical University of Munich Germany

ISBN: (纸本)9798350339598

Recent advances in generative adversarial networks (GANs) allow for the synthesis of extremely photo-realistic face images, deceiving even the most experienced observers, let alone the unsuspecting internet user. Due to this, there has been a considerable effort by the image forensics community to design appropriate tools for the detection of these images. This paper first implements one such detection technique based on spatial and cross-band co-occurrence matrices and convolutional neural networks (CNNs), and then attempts to improve it by introducing additional information obtained from the human gaze. We show that in cases where human observers correctly decide whether an image is real or fake, eye movement information in combination with spatial and cross-band co-occurrence matrices derived from observation regions can be informative towards the task of detecting fake images. However, only a limited increase in the detection accuracy is achieved. © 2023 IEEE.

关键词： Generative adversarial networks

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：