检索结果-内蒙古大学图书馆

1999 Joint SIGDAT Conference on Empirical Methods in Natural language processing and Very Large Corpora, EMNLP 1999

作者： Cucerzan, Silviu Yarowsky, David Department of Computer Science Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

Identifying and classifying personal, geographic, institutional or other names in a text is an important task for numerous applications. This paper describes and evaluates a language-independent bootstrapping algorithm based on iterative learning and re-estimation of contextual and morphological patterns captured in hierarchically smoothed trie models. The algorithm learns from unannotated text and achieves competitive performance when trained on a very short labelled name list with no other required language-specific information, tokenizers or tools. © 1999 Proceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural language processing and Very Large Corpora, EMNLP 1999. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Dynamic nonlocal language modeling via hierarchical topic-based adaptation 37

Dynamic nonlocal language modeling via hierarchical topic-ba...

引用

37th Annual Meeting of the Association for Computational Linguistics, ACL 1999

作者： Florian, Radu Yarowsky, David Computer Science Department and Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

This paper presents a novel method of generating and applying hierarchical, dynamic topic-based language models. It proposes and evaluates new cluster generation, hierarchical smoothing and adaptive topic-probability estimation techniques. These combined models help capture long-distance lexical dependencies. °Experiments on the Broadcast News corpus show significant improvement in perplexity (10.5% overall and 33.5% on target vocabulary). © ACL *** right reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Taking the load off the conference chairs: Towards a digital paper-routing assistant

Taking the load off the conference chairs: Towards a digital...

引用

1999 Joint SIGDAT Conference on Empirical Methods in Natural language processing and Very Large Corpora, EMNLP 1999

作者： Yarowsky, David Florian, Radu Computer Science Department Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21228 United States

This paper describes and extensively evaluates a system for the automatic routing of submitted papers to reviewers and area committees, without the need for any human annotation from the reviewers or the program chair. Routing is based on a profile of previous writings obtainable on-line for the reviewer pool, a generally stable and reusable resource that requires no manual adaptation for new submission streams. The paper explores a wide set of variations and extensions on the core model, and achieves system accuracy approaching that of several human judges on the same task. © 1999 Proceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural language processing and Very Large Corpora, EMNLP 1999. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Distinguishing systems and distinguishing senses: New evaluation methods for Word Sense Disambiguation

引用

Natural language Engineering 1999年第2期5卷 113-133页

作者： Resnik, Philip Yarowsky, David Department of Linguistics and Institute for Advanced Computer Studies University of Maryland College Park MD 20742 United States Department of Computer Science/Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Resnik and Yarowsky (1997) made a set of observations about the state-of-the-art in automatic word sense disambiguation and, motivated by those observations, offered several specific proposals regarding improved evaluation criteria, common training and testing resources, and the definition of sense inventories. Subsequent discussion of those proposals resulted in senseval the first evaluation exercise for word sense disambiguation (Kilgarriff and Palmer 2000). This article is a revised and extended version of our 1997 workshop paper, reviewing its observations and proposals and discussing them in light of the senseval exercise. It also includes a new in-depth empirical study of translingually-based sense inventories and distance measures, using statistics collected from native-speaker annotations of 222 polysemous contexts across 12 languages. These data show that monolingual sense distinctions at most levels of granularity can be effectively captured by translations into some set of second languages, especially as language family distance increases. In addition, the probability that a given sense pair will tend to lexicalize differently across languages is shown to correlate with semantic salience and sense granularity;sense hierarchies automatically generated from such distance matrices yield results remarkably similar to those created by professional monolingual lexicographers. © 1999, Cambridge University Press. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monaural separation of independent acoustical components

Monaural separation of independent acoustical components

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： G. Cauwenberghs Department of Electrical and Computer Engineering and Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

The problem of blindly separating signal mixtures with fewer mixture components than independent signal sources is mathematically ill-defined, and requires suitable prior information on the nature of the sources. Recently, it has been shown that sparse methods for function approximation using a Laplacian prior can be effective, but the method fails to separate a single mixture without further prior information. Other techniques track harmonics, but assume separability in the time-frequency domain. We show that a measure of temporal and spectral coherence provides an effective cue for separating independent acoustical or sonar sources, in the absence of spatial cues in the monaural case. The technique is shown to successfully separate single mixtures of sources with significant spectral overlap.

关键词： Signal processing Independent component analysis Time frequency analysis Data mining Laplace equations Acoustic measurements Sonar measurements Adaptive signal processing Biomedical signal processing Interference

来源：评论

学校读者我要写书评

暂无评论

Realistic 3-D scene modeling from uncalibrated image sequences

Realistic 3-D scene modeling from uncalibrated image sequenc...

引用

IEEE International Conference on Image processing

作者： R. Koch M. Pollefeys Luc Van Gool Multimedia Information Processing Institute of Computer Science University of Kiel Germany ESAT-PSI Center for Processing of Speech and Images Katholieke Universiteit Leuven Belgium

This paper addresses the problem of obtaining photo-realistic 3D models of a scene from images alone with a structure-from-motion approach. The 3D scene is observed from multiple viewpoints by freely moving a camera around the object. No restrictions on camera movement and interval camera parameters like zoom are imposed, as the camera pose and intrinsic parameters are calibrated from the sequence. The only restrictions on the scene content are the rigidity of the scene objects and opaque, piecewise smooth object surfaces. The approach operates independently of object scale and requires only a single low-cost consumer photo or video camera. The modeling system described here uses a three-step approach. First, the camera pose and intrinsic parameters are calibrated on-line by tracking salient feature points between the different views. Next, consecutive images of the sequence are treated as stereoscopic image pairs and dense correspondence maps are computed by area matching. Finally, dense and accurate depth maps are computed by linking together all correspondences over the viewpoints. The depth maps are converted to triangular surfaces meshes that are texture mapped for photo-realistic appearance. The resulting surface models are stored in VRML-format for easy exchange and visualization. The feasibility of the approach has been tested extensively and will be illustrated on several real scenes. In particular we will demonstrate the generation of realistic 3D models for a virtual exhibition of the archaeological excavation site in Sagalassos, Turkey.

关键词： Layout Image sequences Cameras Image reconstruction Calibration Visualization Three dimensional displays Aerospace simulation Discrete event simulation Costs

来源：评论

学校读者我要写书评

暂无评论

Growth Transform of A Sum of Rational Functions and Its Application in Estimating HMM Parameters 5

Growth Transform of A Sum of Rational Functions and Its Appl...

引用

5th International Conference on Spoken language processing, ICSLP 1998

作者： Luo, Xiaoqiang Center for Language and Speech Processing Department of Electrical and Computer Engineering The Johns Hopkins University BaltimoreMD21218 United States

Gopalakrishnan et al [1] described a method called "growth transform" to optimize rational functions over a domain, which has been found useful to train discriminatively Hidden Markov Models(HMM) in speech recognition [5, 6, 9]. A sum of rational functions is encountered when the contributions from other HMM states are weighted in estimating Gaussian parameters of a state, and the weights are optimized using cross-validation [8]. We will show that the growth transform of a sum of rational functions can be obtained by computing term-wise gradients and term-wise function values, as opposed to forming first a single rational function and then applying the result in [1]. This is computationally advantageous when the objective function consists of many rational terms and the dimensionality of the domain is high. We also propose a gradient directed search algorithm to find the appropriate transform constant C. © 1998. 5th International Conference on Spoken language processing, ICSLP 1998. All rights reserved.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

Modeling arbitrarily long sentence-spanning F0 contours by parametric concatenation of word-spanning patterns 5

Modeling arbitrarily long sentence-spanning F0 contours by p...

引用

5th European Conference on speech Communication and Technology, EUROspeech 1997

作者： Fotinea, Evita F. Vlahakis, Michael A. Carayannis, George V. National Technical University of Athens Electrical and Computer Engineering Dpt Division of Computer Science Digital Signal Processing Lab. 9 Heroon Polytechniou St. Zographou 157 73 Athens Greece Institute for Language and Speech Processing 22 Margari St Athens11525 Greece

Modeling FO contours of arbitrarily long and complex sentences of the Greek language may prove to be a difficult task if one considers the various parameters involved, namely focus, position of the prominent vowel within words, syntactic structure and type of expression. None the less, this complexity may be significantly reduced if the expressive requirements of the application area in mind are taken into account. Study of the expressive requirements of the information broadcasting applications revealed that the affirmative type of expression is heavily used and regardless of size and complexity, each sentence-spanning contour may be composed of only four word-spanning patterns. This result not only leads to significant savings in the resources required for a natural sounding speech output but also indicates a highly structured intonative component. © 1997 5th European Conference on speech Communication and Technology, EUROspeech 1997. All rights reserved.

关键词： speech communication

来源：评论

学校读者我要写书评

暂无评论

A biocybernetic simulation of speech perception by humans and animals

A biocybernetic simulation of speech perception by humans an...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： R.I. Damper Image Speech and Intelligent Systems ISIS Research Group Department of Electronics and Computer Science University of Southampton Southampton UK Center for Spoken Language Understanding Department of Computer Science and Engineering Oregon Graduate Institute of Science and Technology Portland OR USA

Important aspects of the voiced/unvoiced categorization of synthetic syllable-initial stop consonants are reproduced by a two stage biocybernetic simulation of the auditory system. This behavior is emergent - it is not explicitly programmed into the model - and no fine timing information is necessary. Unlike real (human and animal) listeners, the computational auditory model can be systematically manipulated and probed to determine the basis of its behavior. This reveals the importance of the region of first formant onset to the perception of voicing for these stimuli. Spectral analysis of this region in the raw stimuli show that processing by the first stage of the model, mimicking the functions of the peripheral auditory system, is not essential to the observed behavior. Thus, in this case at least, the phonetic perception of voicing is directly recoverable from both acoustic and auditory representations of the stimuli.

关键词： Cybernetics Humans Animals Computational modeling Biological system modeling Auditory system speech coding computer science speech processing Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Higher order statistics based Gaussianity test applied to on-line speech processing

Higher order statistics based Gaussianity test applied to on...

引用

Asilomar Conference on Signals, Systems & computers

作者： M. Rangoussi G. Carayannis Department of Electrical Engineering Computer Science Division National and Technical University of Athens Athens Greece Institute of Language and Speech Processing Athens Greece

Detection of speech in noisy recordings becomes a challenging problem when the noise does not follow the usual whiteness, stationarity and high signal-to-noise ratio assumptions. A robust speech detector can affect significantly the performance of several speech processing tasks, such as endpoint detection, segmentation, and finally recognition, if we deal with real life data, as opposed to laboratory or controlled environment recordings. The detector proposed is based on a Gaussianity test that employs third-order cumulants of the data to decide on the binary hypotheses of noise only versus speech plus noise. speech intervals are detected by exploiting the third-order information present in the speech signal. The detector can handle a large family of additive noises, thanks to its third-order statistics basis. The sample-adaptive and decision feedback variations proposed, provide the detector with a tracking ability both with respect to the time variations of speech and the possible nonstationarity of noise. Experiments carried out using real data, recorded in a moving car interior, show satisfactory performance of the proposed algorithms down to -6 dB signal-to-noise ratio.< >

关键词： Higher order statistics Gaussian processes Testing Signal to noise ratio Detectors speech enhancement Working environment noise speech processing Noise robustness Robust control

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：