检索结果-内蒙古大学图书馆

Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition 40

Unsupervised speaker adaptation of deep neural network based...

引用

40th IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2015

作者： Xue, Shaofei Jiang, Hui Dai, Lirong Liu, Qingfeng National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China Hefei China Department of Electrical Engineering and Computer Science York University Toronto Canada

ISBN: (纸本)9781467369978

Recently, we have proposed a general adaptation scheme for deep neural network based on discriminant condition codes and applied it to supervised speaker adaptation in speech recognition based on either frame-level cross-entropy or sequence-level maximum mutual information training criterion [1, 2, 3, 4]. In this case, each condition code is associated with one speaker in data, which is thus called speaker code for convenience. Our previous work has shown that speaker code based methods are quite effective in adapting DNNs even when only a very small amount of adaptation data is available. However, we have to use a large speaker code size and complex processes to obtain the best ASR performance since good initializations of speaker codes and connection weights are very important. In this paper, we propose a method using singular value decomposition (SVD) as in [5] to initialize speaker codes and connection weights to obtain a comparable ASR performance as before but with a smaller speaker code size and much less computation complexity. Meanwhile, we have evaluated unsupervised speaker adaptation with the proposed method in large vocabulary speech recognition in the Switchboard task. Experimental results have shown that it is effective for providing well initializations and suitable in adapting large DNN models. © 2015 IEEE.

关键词： Deep Neural Network (DNN) singular value decomposition (SVD) Speaker Adaptation Speaker Code

来源：评论

学校读者我要写书评

暂无评论

LCCT: A semi-supervised model for sentiment classification

LCCT: A semi-supervised model for sentiment classification

引用

Conference of the North American Chapter of the Association for Computational Linguistics: Human language Technologies, NAACL HLT 2015

作者： Yang, Min Tu, Wenting Lu, Ziyu Yin, Wenpeng Chow, Kam-Pui Department of Computer Science University of Hong Kong Hong Kong Hong Kong Center for Information and Language Processing University of Munich Germany

ISBN: (纸本)9781941643495

Analyzing public opinions towards products, services and social events is an important but challenging task. An accurate sentiment analyzer should take both lexicon-level information and corpus-level information into account. It also needs to exploit the domainspecific knowledge and utilize the common knowledge shared across domains. In addition, we want the algorithm being able to deal with missing labels and learning from incomplete sentiment lexicons. This paper presents a LCCT (Lexicon-based and Corpus-based, Co-Training) model for semi-supervised sentiment classification. The proposed method combines the idea of lexicon-based learning and corpus-based learning in a unified cotraining framework. It is capable of incorporating both domain-specific and domainindependent knowledge. Extensive experiments show that it achieves very competitive classification accuracy, even with a small portion of labeled data. Comparing to state-ofthe-art sentiment classification methods, the LCCT approach exhibits significantly better performances on a variety of datasets in both English and Chinese. © 2015 Association for Computational Linguistics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Uncertainty estimation of DNN classifiers

Uncertainty estimation of DNN classifiers

引用

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Sri Harish Mallidi Tetsuji Ogawa Hynek Hermansky Center for Language and Speech Processing The Johns Hopkins University Baltimore U.S.A Department of Computer Science Waseda University Tokyo Japan Human Language Technology Center of Excellence The Johns Hopkins University Baltimore U.S.A

New efficient measures for estimating uncertainty of deep neural network (DNN) classifiers are proposed and successfully applied to multistream-based unsupervised adaptation of ASR systems to address uncertainty derived from noise. The proposed measure is the error from associative memory models trained on outputs of a DNN. In the present study, an attempt is made to use autoencoders for remembering the property of data. Another measure proposed is an extension of the M-measure, which computes the divergences of probability estimates spaced at specific time intervals. The extended measure results in an improved reliability by considering the latent information of phoneme duration. Experimental comparisons carried out in a multistream-based ASR paradigm demonstrates that the proposed measures yielded improvements over the multistyle trained system and system selected based on existing measures. Fusion of the proposed measures achieved almost the same performance as the oracle system selection.

关键词： Uncertainty Measurement uncertainty speech Noise measurement Training Training data Estimation

来源：评论

学校读者我要写书评

暂无评论

Hybrid orthogonal projection and estimation (HOPE): a new framework to learn neural networks

引用

The Journal of Machine Learning Research 2016年第1期17卷

作者： Kevin Murphy Bernhard Schölkopf Shiliang Zhang Hui Jiang Lirong Dai Google MPI for Intelligent Systems National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei Anhui China Department of Electrical Engineering and Computer Science York UniversityToronto OntarioCanada

In this paper, we propose a novel model for high-dimensional data, called the Hybrid Orthogonal Projection and Estimation (HOPE) model, which combines a linear orthogonal projection and a finite mixture model under a unified generative modeling framework. The HOPE model itself can be learned unsupervised from unlabelled data based on the maximum likelihood estimation as well as discriminatively from labelled data. More interestingly, we have shown the proposed HOPE models are closely related to neural networks (NNs) in a sense that each hidden layer can be reformulated as a HOPE model. As a result, the HOPE framework can be used as a novel tool to probe why and how NNs work, more importantly, to learn NNs in either supervised or unsupervised ways. In this work, we have investigated the HOPE framework to learn NNs for several standard tasks, including image recognition on MNIST and speech recognition on TIMIT. Experimental results have shown that the HOPE framework yields significant performance gains over the current state-of-the-art methods in various types of NN learning problems, including unsupervised feature learning, supervised or semi-supervised learning.

关键词： PCA mixture models neural networks orthogonal projection unsupervised learning von Mises-Fisher (vMF) model

来源：评论

学校读者我要写书评

暂无评论

Author Correction: The challenge of mapping the human connectome based on diffusion tractography

引用

Nature communications 2019年第1期10卷 5059页

作者： Klaus H Maier-Hein Peter F Neher Jean-Christophe Houde Marc-Alexandre Côté Eleftherios Garyfallidis Jidan Zhong Maxime Chamberland Fang-Cheng Yeh Ying-Chia Lin Qing Ji Wilburn E Reddick John O Glass David Qixiang Chen Yuanjing Feng Chengfeng Gao Ye Wu Jieyan Ma Renjie He Qiang Li Carl-Fredrik Westin Samuel Deslauriers-Gauthier J Omar Ocegueda González Michael Paquette Samuel St-Jean Gabriel Girard François Rheault Jasmeen Sidhu Chantal M W Tax Fenghua Guo Hamed Y Mesri Szabolcs Dávid Martijn Froeling Anneriet M Heemskerk Alexander Leemans Arnaud Boré Basile Pinsard Christophe Bedetti Matthieu Desrosiers Simona Brambati Julien Doyon Alessia Sarica Roberta Vasta Antonio Cerasa Aldo Quattrone Jason Yeatman Ali R Khan Wes Hodges Simon Alexander David Romascano Muhamed Barakovic Anna Auría Oscar Esteban Alia Lemkaddem Jean-Philippe Thiran H Ertan Cetingul Benjamin L Odry Boris Mailhe Mariappan S Nadar Fabrizio Pizzagalli Gautam Prasad Julio E Villalon-Reina Justin Galvis Paul M Thompson Francisco De Santiago Requejo Pedro Luque Laguna Luis Miguel Lacerda Rachel Barrett Flavio Dell'Acqua Marco Catani Laurent Petit Emmanuel Caruyer Alessandro Daducci Tim B Dyrby Tim Holland-Letz Claus C Hilgetag Bram Stieltjes Maxime Descoteaux Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg 69120 Germany. k.maier-hein@dkfz.de. Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg 69120 Germany. Sherbrooke Connectivity Imaging Lab (SCIL) Université de Sherbrooke Sherbrooke QC J1K 0A5 QC Canada. Department of Intelligent Systems Engineering School of Informatics and Computing Indiana University Bloomington IN 47408 USA. Krembil Research Institute University Health Network Toronto Canada M5G 2C4. Department of Neurological Surgery University of Pittsburgh School of Medicine Pittsburgh PA 15213 USA. IMT-Institute for Advanced Studies Lucca 55100 Italy. Department of Diagnostic Imaging St. Jude Children's Research Hospital Memphis TN 38105 USA. University of Toronto Institute of Medical Science Toronto Canada M5S 1A8. Institute of Information Processing and Automation Zhejiang University of Technology Hangzhou 310023 Zhejiang China. United Imaging Healthcare Co Shanghai 201807 China. Shanghai Advanced Research Institute Shanghai 201210 China. Laboratory of Mathematics in Imaging Harvard Medical School Boston MA 02215 USA. Center for Research in Mathematics Guanajuato 36023 Mexico. PROVIDI Lab Image Sciences Institute University Medical Center Utrecht Utrecht 3508 The Netherlands. Cardiff University Brain Research Imaging Centre School of Psychology Cardiff University Maindy Road Cardiff CF24 4HQ UK. Department of Radiology University Medical Center Utrecht Utrecht 3508 The Netherlands. Centre de recherche institut universitaire de geriatrie de Montreal (CRIUGM) Université de Montréal Montreal QC Canada H3W 1W5. Sorbonne Universités UPMC Univ Paris 06 CNRS INSERM Laboratoire d'Imagerie Biomédicale (LIB) 75013 Paris France. Center for Advanced Research in Sleep Medicine Hôpital du Sacré-Coeur de Montréal Montreal Canada H4J 1C5. Neuroimaging Unit Institute of Bioimaging and Molecular Physiology (IBFM) Nat

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using emotions to predict user interest areas in online social networks

Using emotions to predict user interest areas in online soci...

引用

International Conference on Data science and Advanced Analytics (DSAA)

作者： Yoad Lewenberg Yoram Bachrach Svitlana Volkova School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Microsoft Research Cambridge United Kingdom Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

ISBN: (纸本)9781467382748

We examine the relation between the emotions users express on social networks and their perceived areas of interests, based on a sample of Twitter users. Our methodology relies on training machine learning models to classify the emotions expressed in tweets, according to Ekman's six high-level emotions. We then used raters, sourced from Amazon's Mechanical Turk, to examine several Twitter profiles and to determine whether the profile owner is interested in various areas, including sports, movies, technology and computing, politics, news, economics, science, arts, health and religion. We find that the propensity of a user to express various emotions correlates with their perceived degree of interest in various areas. We present several models that use the emotional distribution of a Twitter user, as reflected by their tweets, to predict whether they are interested or disinterested in a topic or to determine their degree of interest in a topic.

关键词： Twitter Tagging Advertising Media Electronic mail Predictive models

来源：评论

学校读者我要写书评

暂无评论

Markov Chain Monte Carlo inference on graphical models using event-based processing on the SpiNNaker neuromorphic architecture

Markov Chain Monte Carlo inference on graphical models using...

引用

Annual Conference on Information sciences and Systems (CISS)

作者： Daniel R. Mendat Sang Chin Steve Furber Andreas G. Andreou Department of Electrical and Computer Engineering Johns Hopkins University Baltimore Maryland Applied Physics Laboratory Johns Hopkins University Laurel Maryland School of Computer Science The University of Manchester UK Center for Language and Speech Processing Johns Hopkins University Baltimore Maryland

We present a combined hardware/software architecture to perform Markov Chain Monte Carlo sampling on probabilistic graphical models in a brain-inspired, energy-aware manner. By combining massively-parallel neuromorphic hardware architecture (SpiNNaker) with algorithms we've have developed for the event-based framework employed in SpiNNaker, we achieve large speedups when performing inference as compared to a traditional PC. We present results from two sampling approaches both well suited to the SpiNNaker architecture. Neural sampling, the first of the two approaches relies directly on simulating networks of spiking neurons while the second, Gibb's sampling is more flexible but still takes advantage of the hardware's event-handling capabilities.

关键词： Neurons Graphical models Markov processes Bayes methods Roads computer architecture MATLAB

来源：评论

学校读者我要写书评

暂无评论

Recognition of historical Greek polytonic scripts using LSTM networks

Recognition of historical Greek polytonic scripts using LSTM...

引用

International Conference on Document Analysis and Recognition

作者： Fotini Simistira Adnan Ul-Hassan Vassilis Papavassiliou Basilis Gatos Vassilis Katsouros Marcus Liwicki Institute for Language and Speech Processing Athena Research and Innovation Center Athens Greece Department of Computer Science University of Kaiserslauten Germany NCSR Demokritos Institute of Informatics and Telecommunications Athens Greece DIVA Research Group University of Fribourg Switzerland

ISBN: (纸本)9781479918065

This paper reports on high-performance Optical Character Recognition (OCR) experiments using Long Short-Term Memory (LSTM) Networks for Greek polytonic script. Even though there are many Greek polytonic manuscripts, the digitization of such documents has not been widely applied, and very limited work has been done on the recognition of such scripts. We have collected a large number of diverse document pages of Greek polytonic scripts in a novel database, called Polyton-DB, containing 15; 689 textlines of synthetic and authentic printed scripts and performed baseline experiments using LSTM Networks. Evaluation results show that the character error rate obtained with LSTM varies from 5.51% to 14.68% (depending on the document) and is better than two well-known OCR engines, namely, Tesseract and ABBYY FineReader.

关键词： Logic gates Optical character recognition software Adaptive optics Integrated optics Optical imaging Optical fiber networks Yttrium

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Topology for Energy-Harvesting Heterogeneous Wireless Sensor Networks

Fault-Tolerant Topology for Energy-Harvesting Heterogeneous ...

引用

IEEE International Conference on Communications

作者： Zhiyuan Yin Fan Li Meng Shen Yu Wang Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications School of Computer Science Beijing Institute of Technology Department of Computer Science University of North Carolina at Charlotte

ISBN: (纸本)9781467364300

Recent advances in ambient energy-harvesting wireless sensor networks (WSNs) technologies have made it possible to power the network by energy generated from the environment and thereby increase its lifetime. Various energy sources including light, vibration and heat can be harvested by sensor nodes. However, time-varying energy harvesting also bring new design challenging for WSNs. In this paper, we study a fault-tolerant topology design problem for an energy-harvesting heterogeneous WSN, where multiple supernodes with rich resources are used to improve the performance. We first model the network as a directed and weighted space-time graph in which both spacial and temporal information are preserved. We then define the fault-tolerant topology problem which aims to build a sparser time-varying structure from the original space-time graph while maintaining k-connectivity for the fault-tolerant purpose. Six different algorithms are proposed to solve the problem. Simulation results demonstrate that our proposed methods can save up to around 80% costs.

关键词： Topology Fault tolerance Fault tolerant systems Wireless sensor networks Network topology Ad hoc networks Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

How to protect query and report privacy without sacrificing service quality in participatory sensing

How to protect query and report privacy without sacrificing ...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Meng Li Fan Wu Guihai Chen Liehuang Zhu Zijian Zhang Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Application Beijing Institute of Technology China Department of Computer Science and Engineering Shanghai Jiao Tong University China

The ubiquity of mobile devices has brought forth the concept of participatory sensing, whereby people can collect and share data from ambient environment for the benefit of themselves or community. To encourage participation of all stakeholders and guarantee system functionality, a privacy-preserving participatory sensing system should be established to hide querier's and participant's sensitive information(e.g., interest, location and content). Meanwhile, it is also imperative for server to provide an accurate and quick service(match the “need” with “supply” and retrieve the desired result from collected data set) for queriers when queries and reports are encrypted to protect privacy. In this paper, we propose Query and Report privacy-preserving protocol(QueRe) in participatory sensing system aiming to protect the query privacy and report privacy without sacrificing the service quality. Security analysis and performance simulation show our method achieves superior performance in privacy protection and service quality. To the best of our knowledge, our work is first attempt for protecting query privacy and report privacy while considering server's service quality.

关键词： Privacy Servers Sensors Data privacy Cryptography Protocols Measurement

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：