检索结果-内蒙古大学图书馆

Unsupervised speaker adaptation for phonetic transcription based voice dialing

Second International Confernce on Fuzzy Systems and Knowledge Discovery, FSKD 2005

作者： Kim, Weon-Goo Jang, MinSeok Lee, Chin-Hui School of Electronic and Information Eng. Kunsan National Univ. Biometrics Engineering Research Center Kunsan Chonbuk 573-701 Korea Republic of Dept. of Computer Information Science Kunsan National Univ. Kunsan Chonbuk 573-701 Korea Republic of School of Electrical and Computer Eng. Georgia Institute of Technology Atlanta GA 30332 United States

ISBN: (纸本)9783540283317

Since the speaker independent phoneme HMM based voice dialing system uses only the phoneme transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the speaker dependent system due to the phoneme recognition errors generated when the speaker independent models are used. In order to solve this problem, a new method that jointly estimates the transformation vectors (bias) and transcriptions for the speaker adaptation is presented. The biases and transcriptions are estimated iteratively from the training data of each user with maximum likelihood approach to the stochastic matching using speaker independent phoneme models. Experimental result shows that the proposed method is superior to the conventional method using transcriptions only. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Voice/data communication systems

来源：评论

学校读者我要写书评

暂无评论

Iterative training techniques for phonetic template based speech recognition with a speaker-independent phonetic recognizer

引用

18th Australian Joint Conference on Artificial Intelligence, AI 2005: Advances in Artificial Intelligence

作者： Kim, Weon-Goo Jang, Minseok Lee, Chin-Hui School of Electronic and Information Eng. Kunsan National Univ. Biometrics Engineering Research Center Kunsan Chonbuk 573-701 Korea Republic of Dept. of Computer Information Science Kunsan National Univ. Kunsan Chonbuk 573-701 Korea Republic of School of Electrical and Computer Eng. Georgia Institute of Technology Atlanta GA 30332 United States

ISBN: (纸本)3540304622

This paper presents a new method that improves the performance of the speaker specific phonetic template based speech recognizer with the speaker-independent (SI) phoneme HMMs. Since the phonetic template based speech recognizer uses only the phoneme transcription of the input utterance, the performance of the system is worse than that of the speaker dependent system due to the mismatch between the training data and the SI models. In order to solve these problems, a new training method that iteratively estimates the phonetic templates and transformation vectors for the adaptation of the SI phoneme HMMs is presented. The phonetic class based and codebook-based stochastic matching methods are used to estimate the transformation vectors for speaker adaptation. Performance evaluation using the speaker dependent recognition experiments performed over actual telephone line showed a reduction of about 40% in the error rates when compare to the conventional speaker specific phonetic template based speech recognizer. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

On consistency of stochastic gradient algorithms for ARMAX models with disturbances

On consistency of stochastic gradient algorithms for ARMAX m...

引用

American control Conference (ACC)

作者： Feng Ding Tongwen Chen Research Associate University of Alberta Edmonton Canada Control Science and Engineering Research Center Southern Yangtze University Wuxi China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

ISBN: (纸本)0780390989

In this paper, we give a new method to prove in detail the consistency of the residual based and innovation based stochastic gradient algorithms for identifying CARMA/ARMAX models with disturbances under weaker conditions on statistical properties of the noise, e.g., the mean value is non-zero, and the variance is time-varying, and/or high-order moments are possibly nonexistent. The analysis indicates that the parameter estimation error is consistently bounded, and consistently converges to zero under persistent excitation conditions.

关键词： Stochastic processes Stochastic resonance Parameter estimation Convergence Adaptive control Differential equations Technological innovation Least squares approximation Algorithm design and analysis Least squares methods

来源：评论

学校读者我要写书评

暂无评论

A floated absorbing structure for uncooled microbolometer

A floated absorbing structure for uncooled microbolometer

引用

International Conference on Solid State Sensors and Actuators (TRANSDUCERS)

作者： M.S. Ahn Y.H. Han H.J. Shin K.T. Kim S.H. Lee S. Moon M.H. Oh Microsystem Research Center Korea Institute of Science and Technology South Korea School of Electrical Electronics and Computer Engineering Dankook University South Korea

We propose a versatile infrared (IR) absorbing structure for uncooled infrared detectors. We have designed an infrared absorber consisting of five thin film layers (dielectric layer/protection layer/active layer/supporting layer/reflecting layer) that produce a quarter-wavelength resonance condition. It has excellent thermal properties, which are not influenced by the deformation of the thermal isolation structure. We fabricated a microbolometer with the proposed IR absorption structure by a surface micromachining technology. We estimated an IR absorptance of 80%. This IR absorption structure can be applied to both surface micromachining and bulk micromachining.

关键词： Infrared detectors Electromagnetic wave absorption Micromachining Bolometers Thermal resistance Temperature Resonance Optical surface waves Thermal stresses Voltage

来源：评论

学校读者我要写书评

暂无评论

The design of an LCD system based on the quantitative analysis for enhancement of the motion picture quality

The design of an LCD system based on the quantitative analys...

引用

2005 International Conference on Imaging science, Systems, and Technology: computer Graphics, CISST'05

作者： Lee, Sung-Hak Jang, Soo-Wook Kim, Eun-Su Lee, Dong-Ha Lee, Sang-Hoon Sohng, Kyu-Ik School of Electrical Engineering and Computer Science Kyungpook National University Korea Republic of Digital Network Display Research Lab. Digital Display and Media Company LG Electronics Inc. Korea Republic of TV Product development Development Center LG. Philips LCD Korea Republic of

ISBN: (纸本)9781932415643

The response time of a liquid crystal display device (LCD-RT) is not short enough for video applications, and moreover as the backlight system of conventional hold type, signals in a high temporal frequency over 20Hz have a serious loss of gain. Therefore, the pulsed backlight system has been introduced for reducing motion blurs of LCDs in high motion pictures. But applying the pulsed backlight, full screen flicker and inconsistency of transmissivity for entire frame at a lightening time should be considered. This paper discusses the analysis of blurs in high motion pictures and proposes the design method for more suitable display terminal of LCDs.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Collaborate with strangers to find own preferences 05

Collaborate with strangers to find own preferences

引用

Seventeenth Annual ACM Symposium on Parallelism in Algorithms and Architectures

作者： Awerbuch, Baruch Azar, Yossi Lotker, Zvi Patt-Shamir, Boaz Tuttle, Mark R. Dept. of Computer Science Johns Hopkins University School of Computer Science Tel Aviv University Tel Aviv 69978 Israel Kruislaan 413 CWI 1090 GB Amsterdam Netherlands Dept. of Electrical Engineering Tel Aviv University Tel Aviv 69978 Israel HP Cambridge Research Lab. One Cambridge Center Cambridge MA 02142 United States

ISBN: (纸本)9781581139860

We consider a model with n players and m objects. Each player has a "preference vector" of length m that models his grade for each object. The grades are unknown to the players. A player can learn his grade for an object by probing that object, but performing a probe incurs cost. The goal of a player is to learn his preference vector with minimal cost, by adopting the results of probes performed by other players. To facilitate communication, we assume that players collaborate by posting their grades for objects on a shared billboard: reading from the billboard is free. We consider players whose preference vectors are popular, i.e., players whose preferences are common to many other players. We present distributed and sequential algorithms to solve the problem with logarithmic cost overhead. Copyright 2005 ACM.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Analog and digital avionics signal distribution using WDM

Analog and digital avionics signal distribution using WDM

引用

Conference on Digital Avionics Systems (DASC)

作者： H.H. Refai J.J. Sluss M. Atiquzzaman Hung Nguyen School of Electrical and Computer Engineering University of Oklahama Tulsa OK USA School of Computer Science University of Oklahama Norman OK USA NASA Glenn Research Center Cleveland OH USA

Supporting analog and digital signal transmissions over optical fibers, this paper demonstrates a successful application of wavelength division multiplexing (WDM) to the avionics environment. We characterize the simultaneous transmission of four RF signals (channels) over a single optical fiber. At different points along a fiber optic backbone, these four analog channels are sequentially multiplexed and demultiplexed to more closely emulate the conditions in existing onboard aircraft. We present data from measurements of optical peak power that define the suitability of analog signal transmission, and link throughput that define the suitability of digital signal transmission. The data indicate that WDM is well-suited for the delivery of new inflight services, such as VoWiFi and HDTV.

关键词： Aerospace electronics Wavelength division multiplexing Optical fibers Spine Aircraft Power measurement Throughput HDTV

来源：评论

学校读者我要写书评

暂无评论

A team agent approach to postmarketing surveillance of adverse drug reactions

A team agent approach to postmarketing surveillance of adver...

引用

2005 27th Annual International Conference of the engineering in Medicine and Biology Society, IEEE-EMBS 2005

作者： Ji, Yanqing Ying, Hao Barth-Jones, Daniel C. Yen, John Zhu, Shizhuo Miller, Richard E. Massanari, R. Michael Department of Electrical and Computer Engineering Wayne State University Detroit MI United States Department of Internal Medicine Center for Healthcare Effectiveness Research Wayne State University United States School of Information Science and Technology Pennsylvania State University University Park PA United States Veterans Affairs Medical Center Detroit MI United States

ISBN: (纸本)0780387406

Current postmarketing surveillance methods largely rely on spontaneous reports which suffer from serious underreporting, latency, and inconsistent reporting. Thus they are not ideal for rapidly identifying rare adverse drug reactions (ADRs). We propose an active, multi-agent computer software system, where each agent is empowered with teamwork capabilities such as anticipating information needs, identifying relevant ADR information, and continuously monitoring and proactively sharing such information in a collaborative fashion with other agents. The main purpose of this system is to help regulatory authorities (e.g., FDA in the U.S.) find previously unrecognized ADRs as early as possible. Another objective is to promote increased filing of on-line ADR reports thereby, addressing the severe underreporting problem with the current system. The proposed system has the potential to significantly accelerate the process of ADR discovery and response by utilizing electronic patient data distributed across many different sources and locations more effectively. Our preliminary system design is presented and some issues related to it are discussed. © 2005 IEEE.

关键词： Drug products

来源：评论

学校读者我要写书评

暂无评论

Localized stimulation of and recording from neural cells with fluid injectable neuronal microneedles

Localized stimulation of and recording from neural cells wit...

引用

9th International Conference on Miniaturized Systems for Chemistry and Life sciences, MicroTAS 2005

作者： Paik, Seung-Joon Lee, Ahra Koo, Kyo-In Park, Sunkil Jeong, Myoung-Jun Choi, Hyun Min Lim, Jung-Min Oh, Seung Jae Kim, Sung June Cho, Dongil Dan Automation and Systems Research Institute Seoul National University Seoul 151-742 Korea Republic of School of Electrical Engineering and Computer Science Seoul National University Seoul 151-742 Korea Republic of Nano Bioelectronics and Systems Research Center Seoul National University Seoul 151-742 Korea Republic of Korean Intellectual Property Office Daejeon Korea Republic of

ISBN: (纸本)0974361119

A neuronal microneedle, a single-crystalline silicon microneedle with fluidic microchannels and microelectrodes, is developed for localized stimulation of and recording from neural cells. The neuronal microneedle delivers drugs such as excitatory amino acids at the cellular level as well as electrically records neural signals from neural cells. The fluidic behavior, the mechanical stability, and the electrode-electrolyte interface impedance of the fabricated neuronal microneedle were characterized, respectively. Then, the neural cell responses of a brain of a male Sprague-Dawley rat to a 25μM kainic acid (KA) stimulus were acutely monitored by using the developed neuronal microneedle. Copyright © 2005 by the Transducer research Foundation, Inc.

关键词： Microelectrodes

来源：评论

学校读者我要写书评

暂无评论

A shadow detection and extraction algorithm using digital elevation models and x-band weather radar measurements

引用

International Journal of Remote Sensing 2005年第8期26卷 1531-1549页

作者： Young, Steven D. Kakarlapudi, S. De Haag, M. Uijt National Aeronautics and Space Administration Langley Research Center Hampton VA 23681 United States Ohio University School of Electrical Engineering and Computer Science Athens OH 45701 United States

The aviation industry has been investigating the potential of synthetic and enhanced vision systems (SVS and EVS) to increase the situational awareness of pilots who are operating in low-visibility weather conditions. Synthetic vision displays provide a real-time depiction of a terrain model from the pilot's perspective. To ensure the integrity of this terrain depiction, consistency checking using remote sensing of the terrain environment has been suggested. This requires the detection and extraction of terrain features from both the model and the sensor measurements. Further, the features must be represented in the same reference domain. Terrain shadowing occurs when areas are not in the line-of-sight of the observer. It is these shadowed regions and their morphological characteristics that are identified as the feature domain in which consistency can be assessed between two sources of terrain information. This paper describes an algorithm to extract shadow features from digital elevation models during flight to enable direct comparison with x-band radar modus operandi. Results are presented using flight-test data acquired from two platforms with different radar equipment. The proposed algorithm not only has application to the consistency-checking problem, but also to terrain navigation, image fusion, and digital elevation model accuracy assessments. © 2005 Taylor & Francis Group Ltd.

关键词： Algorithms

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：