检索结果-内蒙古大学图书馆

Speaker and language Recognition Workshop, Odyssey 2014

作者： McCree, Alan Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States

The current state-of-the-art for acoustic language recognition is an i-vector classifier followed by a discriminatively-trained multiclass back-end. This paper presents a unified approach, where a Gaussian i-vector classifier is trained using Maximum Mutual Information (MMI) to directly optimize the multiclass calibration criterion, so that no separate back-end is needed. The system is extended to the open set task by training an additional Gaussian model. Results on the NIST LRE11 standard evaluation task confirm that high performance is maintained with this new single-stage approach. © Odyssey 2014: Speaker and language Recognition Workshop. All rights Reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Predicting Fine-grained Social Roles with Selectional Preferences 52

Predicting Fine-grained Social Roles with Selectional Prefer...

引用

2014 ACL Workshop on language Technologies and Computational Social Science, Science 2014 at the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014

作者： Beller, Charley Harman, Craig Van Durme, Benjamin Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States

ISBN: (纸本)9781941643105

Selectional preferences, the tendencies of predicates to select for certain semantic classes of arguments, have been successfully applied to a number of tasks in computational linguistics including word sense disambiguation, semantic role labeling, relation extraction, and textual inference. Here we leverage the information encoded in selectional preferences to the task of predicting fine-grained categories of authors on the social media platform Twitter. First person uses of verbs that select for a given social role as subject (e.g. I teach... for teacher) are used to quickly build up binary classifiers for that role. © 2014 Association for Computational Linguistics

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Improving speaker recognition performance in the domain adaptation challenge using deep neural networks

Improving speaker recognition performance in the domain adap...

引用

IEEE Spoken language technology Workshop

作者： Daniel Garcia-Romero Xiaohui Zhang Alan McCree Daniel Povey Human Language Technology Center of Excellence & Center for Language and Speech Processing The Johns Hopkins University Baltimore MD USA

Traditional i-vector speaker recognition systems use a Gaussian mixture model (GMM) to collect sufficient statistics (SS). Recently, replacing this GMM with a deep neural network (DNN) has shown promising results. In this paper, we explore the use of DNNs to collect SS for the unsupervised domain adaptation task of the Domain Adaptation Challenge (DAC).We show that collecting SS with a DNN trained on out-of-domain data boosts the speaker recognition performance of an out-of-domain system by more than 25%. Moreover, we integrate the DNN in an unsupervised adaptation framework, that uses agglomerative hierarchical clustering with a stopping criterion based on unsupervised calibration, and show that the initial gains of the out-of-domain system carry over to the final adapted system. Despite the fact that the DNN is trained on the out-of-domain data, the final adapted system produces a relative improvement of more than 30% with respect to the best published results on this task.

关键词： Speaker recognition speech Conferences Training Acoustics Neural networks speech processing

来源：评论

学校读者我要写书评

暂无评论

Global, regional, and national sex-specific burden and control of the HIV epidemic, 1990–2019, for 204 countries and territories: the Global Burden of Diseases Study 2019

引用

The Lancet HIV 2021年第10期8卷 e633-e651页

作者： Jahagirdar, Deepa Walters, Magdalene K. Novotney, Amanda Brewer, Edmond D. Frank, Tahvi D. Carter, Austin Biehl, Molly H. Abbastabar, Hedayat Abhilash, E.S. Abu-Gharbieh, Eman Abu-Raddad, Laith Jamal Adekanmbi, Victor Adeyinka, Daniel Adedayo Adnani, Qorinah Estiningtyas Sakilah Afzal, Saira Aghababaei, Soodabeh Ahinkorah, Bright Opoku Ahmad, Sajjad Ahmadi, Keivan Ahmadi, Sepideh Ahmadpour, Ehsan Ahmed, Muktar Beshir Rashid, Tarik Ahmed Salih, Yusra Ahmed Aklilu, Addis Akram, Tayyaba Akunna, Chisom Joyqueenet Al Hamad, Hanadi Alahdab, Fares Alanezi, Fahad Mashhour Aleksandrova, Ekaterina A. Alene, Kefyalew Addis Ali, Liaqat Alipour, Vahid Almustanyir, Sami Alvis-Guzman, Nelson Ameyaw, Edward Kwabena Amu, Hubert Andrei, Catalina Liliana Andrei, Tudorel Anvari, Davood Arabloo, Jalal Aremu, Olatunde Arulappan, Judie Atnafu, Desta Debalkie Quintanilla, Beatriz Paulina Ayala Ayza, Muluken Altaye Azari, Samad Darshan, B.B. Banach, Maciej Bärnighausen, Till Winfried Barra, Fabio Barrow, Amadou Basu, Sanjay Bazargan-Hejazi, Shahrzad Belay, Habtamu Gebrehana Berheto, Tezera Moshago Bezabhe, Woldesellassie Mequanint Bezabih, Yihienew Mequanint Bhagavathula, Akshaya Srikanth Bhardwaj, Nikha Bhardwaj, Pankaj Bhattacharyya, Krittika Bibi, Sadia Bijani, Ali Bisignano, Catherine Bolarinwa, Obasanjo Afolabi Boloor, Archith Boltaev, Azizbek A. Briko, Nikolay Ivanovich Buonsenso, Danilo Burkart, Katrin Butt, Zahid A. Cao, Chao Charan, Jaykaran Chatterjee, Souranshu Chattu, Soosanna Kumary Chattu, Vijay Kumar Choudhari, Sonali Gajanan Chu, Dinh-Toi Couto, Rosa A.S. Cowden, Richard G. Dachew, Berihun Assefa Dadras, Omid Dagnew, Amare Belachew Dahlawi, Saad M.A. Dai, Xiaochen Dandona, Lalit Dandona, Rakhi das Neves, José Degenhardt, Louisa Demeke, Feleke Mekonnen Desta, Abebaw Alemayehu Deuba, Keshab Dhamnetiya, Deepak Dhungana, Govinda Prasad Dianatinasab, Mostafa Diaz, Daniel Djalalinia, Shirin Doan, Linh Phuong Dorostkar, Fariba Edinur, Hisham Atan Effiong, Andem Eftekharzadeh, Sahar El Sayed Zaki, Maysaa Elayedath, Rajesh Elhadi, Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Division of Allergy and Infectious Diseases University of Washington Seattle WA United States Department of Global Health University of Washington Seattle WA United States School of Social Work University of Washington Seattle WA United States Department of Medicine University of Washington Seattle WA United States Vagelos College of Physicians and Surgeones Columbia University Medical Center New York NY United States Division of Data Analytics and Delivery for Impact WHO Geneva Switzerland Advanced Diagnostic and Interventional Radiology Research Centre Tehran University of Medical Sciences Tehran Iran Multiple Sclerosis Research Centre Tehran University of Medical Sciences Tehran Iran School of Public Health Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Paediatric Chronic Kidney Disease Research Centre Tehran University of Medical Sciences Tehran Iran Department of Psychiatry Tehran University of Medical Sciences Tehran Iran Metabolomics and Genomics Research Centre Tehran University of Medical Sciences Tehran Iran Sina Trauma and Surgery Research Centre Tehran University of Medical Sciences Tehran Iran Research Centre for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Non-Communicable Diseases Research Centre Tehran University of Medical Sciences Tehran Iran Department of Botany Sree Narayana Guru College Chelannur Kozhikode India Clinical Sciences Department University of Sharjah Sharjah United Arab Emirates Mass Communication Department University of Sharjah Sharjah United Arab Emirates Department of Health-Care Policy and Research Weill Cornell Medical College in Qatar Doha Qatar Department of Population Medicine Ca

Background: The sustainable development goals (SDGs) aim to end HIV/AIDS as a public health threat by 2030. Understanding the current state of the HIV epidemic and its change over time is essential to this effort. This study assesses the current sex-specific HIV burden in 204 countries and territories and measures progress in the control of the epidemic. Methods: To estimate age-specific and sex-specific trends in 48 of 204 countries, we extended the Estimation and Projection Package Age-Sex Model to also implement the spectrum paediatric model. We used this model in cases where age and sex specific HIV-seroprevalence surveys and antenatal care-clinic sentinel surveillance data were available. For the remaining 156 of 204 locations, we developed a cohort-incidence bias adjustment to derive incidence as a function of cause-of-death data from vital registration systems. The incidence was input to a custom Spectrum model. To assess progress, we measured the percentage change in incident cases and deaths between 2010 and 2019 (threshold >75% decline), the ratio of incident cases to number of people living with HIV (incidence-to-prevalence ratio threshold <0·03), and the ratio of incident cases to deaths (incidence-to-mortality ratio threshold <1·0). Findings: In 2019, there were 36·8 million (95% uncertainty interval [UI] 35·1–38·9) people living with HIV worldwide. There were 0·84 males (95% UI 0·78–0·91) per female living with HIV in 2019, 0·99 male infections (0·91–1·10) for every female infection, and 1·02 male deaths (0·95–1·10) per female death. Global progress in incident cases and deaths between 2010 and 2019 was driven by sub-Saharan Africa (with a 28·52% decrease in incident cases, 95% UI 19·58–35·43, and a 39·66% decrease in deaths, 36·49–42·36). Elsewhere, the incidence remained stable or increased, whereas deaths generally decreased. In 2019, the global incidence-to-prevalence ratio was 0·05 (95% UI 0·05–0·06) and the global incidence-to-mortality ratio was

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving evaluation and optimization of mt systems against meant 10

Improving evaluation and optimization of mt systems against ...

引用

10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural language processing, EMNLP 2015

作者： Lo, Chi-Kiu Dowling, Philipp C. Wu, Dekai NRC-CNRC Multilingual Text Processing National Research Council Canada 1200 Montreal Road OttawaONK1A 0R6 Canada Tum Fakultät für Informatik Technische Universität München Boltzmannstraße 3 Garching bei München85748 Germany Hkust Human Language Technology Center Hk University of Science and Technology Clear Water Bay Kowloon Hong Kong

ISBN: (纸本)9781941643327

We show that, consistent with MEANTtuned systems that translate into Chinese, MEANT-tuned MT systems that translate into English also outperforms BLEUtuned systems across commonly used MT evaluation metrics, even in BLEU. The result is achieved by significantly improving MEANT's sentence-level ranking correlation with human preferences through incorporating a more accurate distributional semantic model for lexical similarity and a novel backoff algorithm for evaluating MT output which automatic semantic parser fails to parse. The surprising result of MEANT-tuned systems having a higher BLEU score than BLEU-tuned systems suggests that MEANT is a more accurate objective function guiding the development of MT systems towards producing more adequate translation. © EMNLP 2015. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SOME INSIGHTS FROM TRANSLATING CONVERSATIONAL TELEPHONE speech

SOME INSIGHTS FROM TRANSLATING CONVERSATIONAL TELEPHONE SPEE...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Gaurav Kumar Matt Post Daniel Povey Sanjeev Khudanpur Center for Language and Speech Processing & Human Language Technology Center of Excellence The Johns Hopkins University Baltimore MD 21218 USA

ISBN: (纸本)9781479928941

We report insights from translating Spanish conversational telephone speech into English text by cascading an automatic speech recognition (ASR) system with a statistical machine translation (SMT) system. The key new insight is that the informal register of conversational speech is a greater challenge for ASR than for SMT: the BLEU score for translating the reference transcript is 64%, but drops to 32% for translating automatic transcripts, whose word error rate (WER) is 40%. Several strategies are examined to mitigate the impact of ASR errors on the SMT output: (i) providing the ASR lattice, instead of the 1-best output, as input to the SMT system, (ii) training the SMT system on Spanish ASR output paired with English text, instead of Spanish reference transcripts, and (iii) improving the core ASR system. Each leads to consistent and complementary improvements in the SMT output. Compared to translating the 1-best output of an ASR system with 40% WER using an SMT system trained on Spanish reference transcripts, translating the output lattice of a better ASR system with 35% WER using an SMT system trained on ASR output improves BLEU from 32% to 38%.

关键词： speech recognition aquifer storage and recovery Surface mount technology Belgo-Luxembourg Economic Union speech

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Events and Relations Across ACE, ERE, TAC-KBP, and FrameNet Annotation Standards 2

A Comparison of the Events and Relations Across ACE, ERE, TA...

引用

2nd Workshop on EVENTS: Definition, Detection, Coreference, and Representation, EVENTS 2014 at the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014

作者： Aguilar, Jacqueline Beller, Charley McNamee, Paul Van Durme, Benjamin Strassel, Stephanie Song, Zhiyi Ellis, Joe Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States PhiladelphiaPA United States

ISBN: (纸本)9781941643143

The resurgence of effort within computational semantics has led to increased interest in various types of relation extraction and semantic parsing. While various manually annotated resources exist for enabling this work, these materials have been developed with different standards and goals in mind. In an effort to develop better general understanding across these resources, we provide a summary overview of the standards underlying ACE, ERE, TAC-KBP Slot-filling, and FrameNet. © 2014 Association for Computational Linguistics

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Exploring health topics in Chinese social media: An analysis of Sina Weibo 28

Exploring health topics in Chinese social media: An analysis...

引用

28th AAAI Conference on Artificial Intelligence, AAAI 2014

作者： Wang, Shiliang Paul, Michael J. Dredze, Mark Dept. of Computer Science Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD21218 United States

ISBN: (纸本)9781577356752

This paper seeks to identify and characterize health-related topics discussed on the Chinese microblogging website, Sina Weibo. We identified nearly 1 million messages containing health-related keywords, filtered from a dataset of 93 million messages spanning five years. We applied probabilistic topic models to this dataset and identified the prominent health topics. We show that a variety of health topics are discussed in Sina Weibo, and that four flu-related topics are correlated with monthly influenza case rates in China. © Copyright 2014, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

FEATHERWEIGHT PHONETIC KEYWORD SEARCH FOR CONVERSATIONAL speech

FEATHERWEIGHT PHONETIC KEYWORD SEARCH FOR CONVERSATIONAL SPE...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Keith Kintzley Aren Jansen Hynek Hermansky U.S. Naval Academy Annapolis MD USA Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

ISBN: (纸本)9781479928941

The point process model (PPM) for keyword search is a phonetic event-driven approach that provides a whole-word focused alternative to fast lattice matching techniques. Recent efforts in PPMs have been focused on improved model estimation techniques and efficient search algorithms, but past evaluations have been limited to searching relatively easy scripted corpora for simple unigram queries, preventing comprehensive benchmarking against standard search methods. In this paper, we present techniques for score normalization and the processing of multi-word and out of training query terms as required by the 2006 NIST Spoken Term Detection (STD) evaluation, permitting the first comprehensive benchmark of PPM search technology against state-of-the-art word and phonetic-based search systems. We demonstrate PPM to be the fastest phonetic system while posting accuracies competitive with the best phonetic alternatives. Moreover, index construction time and size are better than any keyword search system entered in the NIST evaluation.

关键词： SEARCHING ALGORITHM Pulse position modulation Key Search search systems Estimation Techniques KEYWORD phonetics Search methods speech NIST

来源：评论

学校读者我要写书评

暂无评论

A joint graph inference case study: the C. elegans chemical and electrical connectomes

引用

Worm 2016年第2期5卷 e1142041页

作者： Li Chen Joshua T Vogelstein Vince Lyzinski Carey E Priebe Software and Service Group Intel Corporation Hillsboro OR USA. Department of Biomedical Engineering and Institute for Computational Medicine Johns Hopkins University Baltimore MD USA. Johns Hopkins University Human Language Technology Center of Excellence Baltimore MD USA. Department of Applied Mathematics and Statistics Johns Hopkins University Baltimore MD USA.

We investigate joint graph inference for the chemical and electrical connectomes of the Caenorhabditis elegans roundworm. The C. elegans connectomes consist of [Formula: see text] non-isolated neurons with known functional attributes, and there are two types of synaptic connectomes, resulting in a pair of graphs. We formulate our joint graph inference from the perspectives of seeded graph matching and joint vertex classification. Our results suggest that connectomic inference should proceed in the joint space of the two connectomes, which has significant neuroscientific implications.

关键词： fusion inference joint graph inference joint vertex classification neural connectome omnibus embedding seeded graph matching

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：