检索结果-内蒙古大学图书馆

Phonetically balanced and psychometrically equivalent monosyllabic word lists for word recognition testing in Thai

Proceedings of Meetings on Acoustics 2015年第1期25卷

作者： Sajeerat Poonyaban Pasinee Aungsakulchai Charturong Tantibundhit Chutamanee Onsuwan Rattinan Tiravanitchakul Krit Kosawat Adirek Munthuli 1Center of Excellence in Intelligent Informatics Speech and Language Technology and Service Innovation (CILS) Thammasat University Thailand 2Department of Electrical and Computer Engineering Faculty of Engineering Thammasat University Rangsit Campus Khlong Luang Pathum Thani Thailand pond_poonyaban@*** meilyp.aung@*** tchartur@engr.tu.ac.th ***@student.tu.ac.th 3Department of English and Linguistics Faculty of Liberral Arts Thammasat University Rangsit Campus Khlong Luang Pathum Thani Thailand consuwan@tu.ac.th 4Department of Communication Science and Disorders Faculty of Medicine Mahidol University Thailand rartv@*** 5NECTEC National Science and Technology Development Agency (NSTDA) Pathum Thani Thailand krit.kosawat@nectec.or.th

Word recognition testing may be defined as a procedure to assess a listener’s ability to identify one-syllable words (such as phonetically-balanced/PB words) that are presented at a given suprathreshold level to arrive at a word recognition score. For Thai, Thammasat University and Ramathibodi Hospital Phonetically Balanced Word Lists 2015 (TU-RAMA PB’15) were created with five lists, each with 25 monosyllabic words. Besides its phoneme distributions being based on large-scale Thai spoken corpora, TU-RAMA PB’15 is in line with TU PB’14 with emphasis on phonetic balance, symmetrical phoneme occurrence, and word familiarity. To evaluate its homogeneity in terms of decibel intelligibility, the lists were recorded and presented to 10 normal hearing participants, ranging from 0 to 50 dB HL in 2 dB increments (ascending order) until they repeated correct verbal responses. Using logistic regression, regression slopes and intercepts were calculated to estimate percentage of correct performance at any given intensity and to construct psychometric functions for every list. Derived psychometric function slopes ranged from 0.2015 to 0.2262 while intensities required for 50% intelligibility ranged from 17.0876 to 20.8856. Two-way Chi-Square analysis performed on both parameters indicated that there was no significant difference among the five lists.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-level Statistical Machine Translation 6

Meta-level Statistical Machine Translation

引用

6th International Joint Conference on Natural language Processing, IJCNLP 2013

作者： Ebrahimi, Sajad Meshgi, Kourosh Khadivi, Shahram Abady, Mohammad Ebrahim Shiri Ahmad Human Language Technology Lab Amirkabir University of Technology Tehran Iran Graduate School of Informatics Kyoto University Kyoto Japan Department of Computer Science Amirkabir University of Technology Tehran Iran

ISBN: (纸本)9784990734800

We propose a simple and effective method to build a meta-level Statistical Machine Translation (SMT), called meta-SMT, for system combination. Our approach is based on the framework of Stacked Generalization, also known as Stacking, which is an ensemble learning algorithm, widely used in machine learning tasks. First, a collection of base-level SMTs is generated for obtaining a meta-level corpus. Then a meta-level SMT is trained on this corpus. In this paper we address the issue of how to adapt stacked generalization to SMT. We evaluate our approach on English-to-Persian machine translation. Experimental results show that our approach leads to significant improvements in translation quality over a phrase-based baseline by about 1.1 BLEU points. © IJCNLP *** right reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Dirt cheap web-scale parallel text from the Common Crawl

Dirt cheap web-scale parallel text from the Common Crawl

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Smith, Jason R. Koehn, Philipp Saint-Amand, Herve Callison-Burch, Chris Plamada, Magdalena Lopez, Adam Department of Computer Science Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States School of Informatics University of Edinburgh United Kingdom Institute of Computational Linguistics University of Zurich Switzerland Computer and Information Science Department University of Pennsylvania United States

ISBN: (纸本)9781937284503

Parallel text is the fuel that drives modern machine translation systems. The Web is a comprehensive source of preexisting parallel text, but crawling the entire web is impossible for all but the largest companies. We bring web-scale parallel text to the masses by mining the Common Crawl, a public Web crawl hosted on Amazon's Elastic Cloud. Starting from nothing more than a set of common two-letter language codes, our open-source extension of the STRAND algorithm mined 32 terabytes of the crawl in just under a day, at a cost of about $500. Our large-scale experiment uncovers large amounts of parallel text in dozens of language pairs across a variety of domains and genres, some previously unavailable in curated datasets. Even with minimal cleaning and filtering, the resulting data boosts translation performance across the board for five different language pairs in the news domain, and on open domain test sets we see improvements of up to 5 BLEU. We make our code and data available for other researchers seeking to mine this rich new data resource.1 © 2013 Association for Computational Linguistics.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

OPEN VOCABULARY HANDWRITING RECOGNITION USING COMBINED WORD-LEVEL AND CHARACTER-LEVEL language MODELS

OPEN VOCABULARY HANDWRITING RECOGNITION USING COMBINED WORD-...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Michal Kozielski David Rybach Stefan Hahn Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781479903573

In this paper, we present a unified search strategy for open vocabulary handwriting recognition using weighted finite state transducers. Additionally to a standard word-level language model we introduce a separate n-gram character-level language model for out-of-vocabulary word detection and recognition. The probabilities assigned by those two models are combined into one Bayes decision rule. We evaluate the proposed method on the IAM database of English handwriting. An improvement from 22.2% word error rate to 17.3% is achieved comparing to the closed-vocabulary scenario and the best published result.

关键词： Handwriting Vocabulary modelling languages search strategies Error analysis Word Bayes Decision Rule handwriting recognition

来源：评论

学校读者我要写书评

暂无评论

FEATURE COMBINATION AND STACKING OF RECURRENT AND NON-RECURRENT NEURAL NETWORKS FOR LVCSR

FEATURE COMBINATION AND STACKING OF RECURRENT AND NON-RECURR...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Christian Plahl Michael Kozielski Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University

ISBN: (纸本)9781479903573

This paper investigates the combination of different short-term features and the combination of recurrent and non-recurrent neural networks (NNs) on a Spanish speech recognition task. Several methods exist to combine different feature sets such as concatenation or linear discriminant analysis (LDA). Even though all these techniques achieve reasonable improvements, feature combination by multi-layer perceptrons (MLPs) outperforms all known approaches. We develop the concept of MLP based feature combination further using recurrent neural networks (RNNs). The phoneme posterior estimates derived from an RNN lead to a significant improvement over the result of the MLPs and achieve a 5% relative better word error rate (WER) with much less parameters. Moreover, we improve the system performance further by combining an MLP and an RNN in a hierarchical framework. The MLP benefits from the preprocessing of the RNN. All NNs are trained on phonemes. Nevertheless, the same concepts could be applied using context-dependent states. In addition to the improvements in recognition performance w.r.t. WER, NN based feature combination methods reduce both, the training and the testing complexity. Overall, the systems are based on a single set of acoustic models, together with the training of different NNs.

关键词： Feature combination Multi-layer perceptron Recurrent neural networks Long-short-term-memory Speech recognition recurrent neural nets Speech recognition CSRP3 gene Stacking Neural network System performance Training

来源：评论

学校读者我要写书评

暂无评论

Sequential UBM adaptation for speaker verification

Sequential UBM adaptation for speaker verification

引用

2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013

作者： Wang, Jun Wang, Dong Wu, Xiaojun Zheng, Thomas Fang Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China Center for Speech and Language Technologies Research Institute of Information Technology Tsinghua University Beijing 100084 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9781479910434

GMM-UBM-based speaker verification heavily relies on a well trained UBM. In practice, it is not often easy to obtain an UBM that fully matches acoustic channels in operation. To solve this problem, we propose a novel sequential MAP adaptation approach: by being sequentially updated with data from new enrollments, the UBM learns and converges to the working channel. Our experiments are conducted on a time-varying speech database, with two channel-mismatched UBMs as the initial model. The results confirm that the sequential UBM adaptation provides significant performance improvement, leading to a relative EER reduction of 6.3% and 14.8% for the two mismatched UBMs, respectively. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Formative feedback in interactive learning environments

Formative feedback in interactive learning environments

引用

16th International Conference on Artificial Intelligence in Education, AIED 2013

作者： Goldin, Ilya M. Martin, Taylor Baker, Ryan Aleven, Vincent Barnes, Tiffany Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States Department of Instructional Technology and Learning Sciences Utah State University Logan UT United States Department of Human Development Teachers College Columbia University New York City NY United States Department of Computer Science North Carolina State University Raleigh NC United States

ISBN: (纸本)9783642391118

Educators and researchers have long recognized the importance of formative feedback for learning. Formative feedback helps learners understand where they are in a learning process, what the goal is, and how to reach that goal. While experimental and observational research has illuminated many aspects of feedback, modern interactive learning environments provide new tools to understand feedback and its relation to various learning outcomes. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

On constant-weight multi-valued sequences from cyclic difference sets

On constant-weight multi-valued sequences from cyclic differ...

引用

作者： Kaida, Takayasu Zheng, Junru Department of Information and Computer Sciences Faculty of Humanity-Oriented Science and Engineering Kinki University Iizuka-shi 820-8555 Japan Department of Human Development Faculty of Humanities Kyushu Women's University Kitakyushu-shi 807-8586 Japan

We proposed a method for constructing constant-weight and multi-valued sequences from the cyclic difference sets by generalization of the method in binary case proposed by N. Li, X. Zeng and L. Hu in 2008. In this paper we give some properties about sets of such sequences and it is shown that a set of non-constant-weight sequences over Z4 with length 13 from the (13,4, l)-cyclic difference set, and a set of constant-weight sequences over Z5 with length 21 from the (21,5, l)-cyclic difference set have almost highest linear complexities and good profiles of all sequences' linear complexities. Moreover we investigate the value distribution, the linear complexity and correlation properties of a set of sequences with length 57 over GF(8) from the (57,8, l)-cyclic difference set. It is pointed out that this set also has good value distributions and almost highest linear complexities in similar to previous two sets over Z4 with length 13 and Z5 with length 21. Copyright © 2013 The Institute of Electronics, Information and Communication Engineers.

关键词： Set theory

来源：评论

学校读者我要写书评

暂无评论

Morpheme-based feature-rich language models using Deep Neural Networks for LVCSR of Egyptian Arabic

Morpheme-based feature-rich language models using Deep Neura...

引用

2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013

作者： El-Desoky Mousa, Amr Kuo, Hong-Kwang Jeff Mangu, Lidia Soltau, Hagen Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany IBM T. J. Watson Research Center Yorktown Heights NY 10598 United States

ISBN: (纸本)9781479903566

Egyptian Arabic (EA) is a colloquial version of Arabic. It is a low-resource morphologically rich language that causes problems in Large Vocabulary Continuous Speech Recognition (LVCSR). Building LMs on morpheme level is considered a better choice to achieve higher lexical coverage and better LM probabilities. Another approach is to utilize information from additional features such as morphological tags. On the other hand, LMs based on Neural Networks (NNs) with a single hidden layer have shown superiority over the conventional n-gram LMs. Recently, Deep Neural Networks (DNNs) with multiple hidden layers have achieved better performance in various tasks. In this paper, we explore the use of feature-rich DNN-LMs, where the inputs to the network are a mixture of words and morphemes along with their features. Significant Word Error Rate (WER) reductions are achieved compared to the traditional word-based LMs. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Can Internet usage positively or negatively affect interpersonal relationship?

Smart Innovation, Systems and Technologies

引用

Smart Innovation, Systems and Technologies 2013年 20卷 373-382页

作者： Lai, Chih-Hung Lin, Chunn-Ying Chen, Cheng-Hung Gwung, Hwei-Ling Li, Chia-Hao Department of Computer Science and Information Engineering National Dong Hwa University Hualien Taiwan Department of Early Childhood Education National Dong Hwa University Hualien Taiwan Department of Educational Administration and Mangement National Dong Hwa University Hualien Taiwan Department of Curriculum Design and Human Potentials Development National Dong Hwa University 1 Sec. 2 Da Hsueh Rd. Shou-Feng Hualien 974 Taiwan

ISBN: (纸本)9783642354519

Many past studies showed that Internet addiction negatively affected the interpersonal relationship. However, new functions on the Internet provide more online interactions, especially some social websites such as Facebook which enables individuals to establish new relationships with acquaintances, as well as maintain close relationships with friends. This drives us to the questions whether the Internet is detrimental to one's interpersonal relationship or whether, instead, it might enhance one's interpersonal relationship. This study examined the association among Internet addiction, various Internet usage, and interpersonal relationships. In total, 444 valid copies of questionnaires were collected from a university. The results indicated that the Internet functions on social interaction, video watching, and information seeking can enhance interpersonal relationship while porn-website surfing and game playing cannot directly affect interpersonal relationship. On the other hand, the social interaction, porn-website surfing, and video watching led to poor interpersonal relationship mediated by Internet addiction. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Surveys

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：