检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Żelasko, Piotr Feng, Siyuan Velázquez, Laureano Moro Abavisani, Ali Bhati, Saurabhchand Scharenborg, Odette Hasegawa-Johnson, Mark Dehak, Najim Center of Language and Speech Processing The Johns Hopkins University 3400 North Charles Street BaltimoreMD21218 United States Human Language Technology Center of Excellence The Johns Hopkins University 810 Wyman Park Drive BaltimoreMD21218 United States Multimedia Computing Group Delft University of Technology Van Mourik Broekmanweg 6 Delft2628 XE Netherlands Department of Electrical and Computer Engineering University of Illinois 405 N Mathews UrbanaIL61801 United States

The high cost of data acquisition makes Automatic speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well as zero-shot learning in order to build ASR systems for these low-resource languages. While it has been shown that the pooling of resources from multiple languages is helpful, we have not yet seen a successful application of an ASR model to a language unseen during training. A crucial step in the adaptation of ASR from seen to unseen languages is the creation of the phone inventory of the unseen language. The ultimate goal of our work is to build the phone inventory of a language unseen during training in an unsupervised way without any knowledge about the language. In this paper, we 1) investigate the influence of different factors (i.e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language;2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation;and 3) present different methods to build a phone inventory of an unseen language in an unsupervised way. To that end, we conducted mono-, multi-, and crosslingual experiments on a set of 13 phonetically diverse languages and several in-depth analyses. We found a number of universal phone tokens (IPA symbols) that are well-recognized cross-linguistically. Through a detailed analysis of results, we conclude that unique sounds, similar sounds, and tone languages remain a major challenge for phonetic inventory discovery. © 2022, CC BY-NC-ND.

关键词： Telephone sets

来源：评论

学校读者我要写书评

暂无评论

Evaluating Neural Machine Comprehension Model Robustness to Noisy Inputs and Adversarial Attacks

arXiv

引用

arXiv 2020年

作者： Wu, Winston Arendt, Dustin Volkova, Svitlana Center for Language and Speech Processing Department of Computer Science Johns Hopkins University Visual Analytics Group Data Sciences and Analytics Group Pacific Northwest National Laboratory

We evaluate machine comprehension models’ robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model confidence and misclassification rate, and contrast model performance in adversarial training with different embedding types on two benchmark datasets. We demonstrate improving model performance with ensembling. Finally, we analyze factors that effect model behavior under adversarial training and develop a model to predict model errors during adversarial attacks. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Mask ctc: Non-Autoregressive end-To-end asr with ctc and mask predict

arXiv

引用

arXiv 2020年

作者： Higuchi, Yosuke Watanabe, Shinji Chen, Nanxin Ogawa, Tetsuji Kobayashi, Tetsunori Center for Language and Speech Processing Johns Hopkins University Baltimore United States Department of Communications and Computer Engineering Waseda University Tokyo

We present Mask CTC, a novel non-Autoregressive end-To-end automatic speech recognition (ASR) framework, which generates a sequence by refining outputs of the connectionist temporal classification (CTC). Neural sequence-To-sequence models are usually autoregressive: each output token is generated by conditioning on previously generated tokens, at the cost of requiring as many iterations as the output length. On the other hand, non-Autoregressive models can simultaneously generate tokens within a constant number of iterations, which results in significant inference time reduction and better suits end-Toend ASR model for real-world scenarios. In this work, Mask CTC model is trained using a Transformer encoder-decoder with joint training of mask prediction and CTC. During inference, the target sequence is initialized with the greedy CTC outputs and low-confidence tokens are masked based on the CTC probabilities. Based on the conditional dependence between output tokens, these masked low-confidence tokens are then predicted conditioning on the high-confidence tokens. Experimental results on different speech recognition tasks show that Mask CTC outperforms the standard CTC model (e.g., 17.9% ! 12.1% WER on WSJ) and approaches the autoregressive model, requiring much less inference time using CPUs (0.07 RTF in Python implementation). All of our codes will be publicly available. Copyright © 2020, The Authors. All rights reserved.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Large Generative Model Assisted 3D Semantic Communication

arXiv

引用

arXiv 2024年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction;2) Latent semantic redundancy;and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State Information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Twitter Social Mobility Index: Measuring Social Distancing Practices from Geolocated Tweets

arXiv

引用

arXiv 2020年

作者： Xu, Paiheng Dredze, Mark Broniatowski, David A. Malone Center for Engineering in Healthcare Center for Language and Speech Processing Department of Computer Science Johns Hopkins University Department of Engineering Management and Systems Engineering Institute for Data Democracy and Politics The George Washington University

Social distancing is an important component of the response to the novel Coronavirus (COVID-19) pandemic. Minimizing social interactions and travel reduces the rate at which the infection spreads, and"flattens the curve" such that the medical system can better treat infected individuals. However, it remains unclear how the public will respond to these policies. This paper presents the Twitter Social Mobility Index, a measure of social distancing and travel derived from Twitter data. We use public geolocated Twitter data to measure how much a user travels in a given week. We find a large reduction in travel in the United States after the implementation of social distancing policies, with larger reductions in states that were early adopters and smaller changes in states without policies. Our findings are presented on http://*** and we will continue to update our analysis during the pandemic. Copyright © 2020, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

NITS-VC system for VATEX video captioning challenge 2020

arXiv

引用

arXiv 2020年

作者： Singh, Alok Singh, Thoudam Doren Bandyopadhyay, Sivaji Center for Natural Language Processing Department of Computer Science and Engineering National Institute of Technology Silchar Assam India

Video captioning is process of summarising the content, event and action of the video into a short textual form which can be helpful in many research areas such as video guided machine translation, video sentiment analysis and providing aid to needy individual. In this paper, a system description of the framework used for VATEX-2020 video captioning challenge is presented. We employ an encoder-decoder based approach in which the visual features of the video are encoded using 3D convolutional neural network (C3D) and in the decoding phase two Long Short Term Memory (LSTM) recurrent networks are used in which visual features and input captions are fused separately and final output is generated by performing element-wise product between the output of both LSTMs. Our model is able to achieve BLEU scores of 0.20 and 0.22 on public and private test data sets respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Sequence to multi-sequence learning via conditional chain mapping for mixture signals 20

Sequence to multi-sequence learning via conditional chain ma...

引用

Proceedings of the 34th International Conference on Neural Information processing Systems

作者： Jing Shi Xuankai Chang Pengcheng Guo Shinji Watanabe Yusuke Fujita Jiaming Xu Bo Xu Lei Xie Center for Language and Speech Processing Johns Hopkins University and Institute of Automation Chinese Academy of Sciences (CASIA) Beijing China Center for Language and Speech Processing Johns Hopkins University Center for Language and Speech Processing Johns Hopkins University and ASLP@NPU School of Computer Science Northwestern Polytechnical University Xi'an China Hitachi Ltd. Research & Development Group Japan Institute of Automation Chinese Academy of Sciences (CASIA) Beijing China ASLP@NPU School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781713829546

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence. We extend the standard sequence-to-sequence model to a conditional multi-sequence model, which explicitly models the relevance between multiple output sequences with the probabilistic chain rule. Based on this extension, our model can conditionally infer output sequences one-by-one by making use of both input and previously-estimated contextual output sequences. This model additionally has a simple and efficient stop criterion for the end of the transduction, making it able to infer the variable number of output sequences. We take speech data as a primary test field to evaluate our methods since the observed speech data is often composed of multiple sources due to the nature of the superposition principle of sound waves. Experiments on several different tasks including speech separation and multi-speaker speech recognition show that our conditional multi-sequence models lead to consistent improvements over the conventional non-conditional models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving solutions in the Industrial Internet of Things

Privacy-preserving solutions in the Industrial Internet of T...

引用

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： George Drosatos Konstantinos Rantos Dimitris Karampatzakis Thomas Lagkas Panagiotis Sarigiannidis Institute for Language and Speech Processing Athena Research Center Xanthi Greece Department of Computer Science International Hellenic University Kavala Greece Dept. of Electrical and Computer Engineering University of Western Macedonia Kozani Greece

ISBN: (数字)9781728143514

ISBN: (纸本)9781728198040

Industrial Internet of Things (IIoT) is a relatively new area of research that utilises multidisciplinary and holistic approaches to develop smart solutions for complex problems in industrial environments. Designing applications for the IIoT is a non trivial issue and requires to address, among many others, technology concerns, the protection of personal data, and the privacy of individuals. In this review paper, we identify privacy-preserving solutions that have been proposed in the literature to safeguard the privacy of individuals being part, or interacting with, the IIoT environment. As such, it considers two main categories of the analysed protocols, i.e., the privacy-preserving data management and processing solutions, and the privacy-preserving authentication methods.

关键词： Privacy Encryption Authentication

来源：评论

学校读者我要写书评

暂无评论

δ-Calculus:A New Approach to Quantifying Location Privacy

引用

computers, Materials & Continua 2020年第6期63卷 1323-1342页

作者： Lihua Yin Ran Li Jingquan Ding Xiao Li Yunchuan Guo Huibing Zhang Ang Li Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China Institute of Information Engineering CASBeijing100093China Xinjiang Technical Institute of Physics&Chemistry Chinese Academy ScienceUrumqi830011China Key laboratory of Speech Language Information Processing of Xinjiang Urumqi830046China University of Chinese Academy of Sciences Beijing100049China Guilin University of Electronic Technology Guilin541004China Department of Electrical and Computer Engineering Duke UniversityDurham27708USA

With the rapid development of mobile wireless Internet and high-precision localization devices,location-based services(LBS)bring more convenience for people over recent *** LBS,if the original location data are directly provided,serious privacy problems *** a response to these problems,a large number of location-privacy protection mechanisms(LPPMs)(including formal LPPMs,FLPPMs,etc.)and their evaluation metrics have been proposed to prevent personal location information from being leakage and quantify privacy ***,existing schemes independently consider FLPPMs and evaluation metrics,without synergizing them into a unifying *** this paper,a unified model is proposed to synergize FLPPMs and evaluation *** detail,the probabilistic process calculus(calledδ-calculus)is proposed to characterize obfuscation schemes(which is a LPPM)and integrateα-entropy toδ-calculus to evaluate its privacy ***,we use two calculus moving and probabilistic choice to model nodes’mobility and compute its probability distribution of nodes’locations,and a renaming function to model privacy *** formally defining the attacker’s ability and extending relative entropy,an evaluation algorithm is proposed to quantify the leakage of location ***,a series of examples are designed to demonstrate the efficiency of our proposed approach.

关键词： Location privacy δ-calculus relative entropy

来源：评论

学校读者我要写书评

暂无评论

Measuring pitch extractors' response to frequency-modulated multi-component signals

arXiv

引用

arXiv 2022年

作者： Kawahara, Hideki Yatabe, Kohei Sakakibara, Ken-Ichi Kitamura, Tatsuya Banno, Hideki Morise, Masanori Center for Innovative Research and Liaison Wakayama University Wakayama640-8510 Japan Department of Electrical Engineering and Computer Science Tokyo University of Agriculture and Technology Tokyo184-8588 Japan Department of Speech-Language-Hearing Therapy Health Science University of Hokkaido Hokkaido Sapporo061-0293 Japan Faculty of Intelligence and Informatics Konan University Hyogo Kobe658-8501 Japan Department of Information Engineering Meijo University Aichi Nagoya468-8502 Japan Department of Frontier Media Science Meiji University Tokyo164-8525 Japan

This article focuses on the research tool for investigating the fundamental frequencies of voiced sounds. We introduce an objective and informative measurement method of pitch extractors' response to frequency-modulated tones. The method uses a new test signal for acoustic system analysis. The test signal enables simultaneous measurement of the extractors' responses. They are the modulation frequency response and the total distortion, including intermodulation distortions. We applied this method to various pitch extractors and placed them on several performance maps. We used the proposed method to fine-tune one of the extractors to make it the best fit tool for scientific research of voice fundamental *** Codes 94A12, 93C80, 42-08 Copyright © 2022, The Authors. All rights reserved.

关键词： Frequency modulation

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：