Search For:

Displaying 1-50 out of 52 total
Computer-Assisted Audiovisual Language Learning
Found in: Computer
By Lijuan Wang,Yao Qian,Matthew Scott,Gang Chen,Frank Soong
Issue Date:June 2012
pp. 38-47
Advances in speech-processing technology have enabled novel ways to learn a foreign language online. With Engkoo, researchers in China are working to turn any computer into a language learning assistant and make searching a language easier. The featured We...
 
An integrated vehicular and urban sensing system: Framework and modeling
Found in: Information Networking, International Conference on
By Adnan Nasir,Hock Beng Lim,Boon Hee Soong
Issue Date:February 2012
pp. 159-164
We present the framework design and modeling for an integrated vehicular and human-centric urban sensing system. The goal is to understand the impact of vehicles and human activities on the surrounding environment. This is achieved through a seamless integ...
 
Global Wireless Machine-to-Machine Standardization
Found in: IEEE Internet Computing
By Kim Chang,A Soong,M Tseng, Zhixian Xiang
Issue Date:March 2011
pp. 64-69
Machine-to-machine (M2M) communications are gaining more prominence in wireless communication. However, the current systems are optimized more for human-to-human (H2H) than M2M communications. Therefore it's important that wireless technologies evolve and ...
 
Home Alone Faint Detection Surveillance System Using Thermal Camera
Found in: Computer Research and Development, International Conference on
By Wai Kit Wong, Hong Liang Lim, Chu Kiong Loo, Way Soong Lim
Issue Date:May 2010
pp. 747-751
Fainting is the unwanted event occur amongst the senior citizens, patients or pregnant women. This event can cause physical injuries or even mental problems. In this paper, we proposed a simple faint detection algorithm apply into a thermal imaging camera ...
 
Wireless Webcam Based Omnidirectional Health Care Surveillance System
Found in: Computer Research and Development, International Conference on
By Wai Kit Wong, Yen Chee Poh, Chu Kiong Loo, Way Soong Lim
Issue Date:May 2010
pp. 712-716
This paper proposes an efficient omnidirectional surveillance system for health care purposes. The proposed surveillance system is used to detect fainted person at health care centers such as old folk's home, hospital, and handicapped center and is located...
 
An Effective Trespasser Detection System Using Thermal Camera
Found in: Computer Research and Development, International Conference on
By Wai Kit Wong, Zeh Yang Chew, Chu Kiong Loo, Way Soong Lim
Issue Date:May 2010
pp. 702-706
This paper presents a novel human detection algorithm embedded into a thermal imaging system to form a fast and effective trespasser detection system for smart surveillance purpose. To identify a human object, pattern recognization technique is employed wh...
 
An Asymmetric Similarity Measure for Ontologies Based on the Feature Contrast Model
Found in: Complex, Intelligent and Software Intensive Systems, International Conference
By Watson Wei Khong Chua, Angela Eck Soong Goh
Issue Date:February 2010
pp. 1002-1007
Ontology alignment is a time consuming process, especially when the two ontologies to be aligned are large. A fast and accurate ontology similarity can help the user to avoid aligning ontologies without significant similarities. In this paper, we propose a...
 
Adaptive Case Based Reasoning for Fault Diagnosis
Found in: Soft Computing and Pattern Recognition, International Conference of
By Pang Shen Yee, Loo Chu Kiong, Lim Way Soong
Issue Date:December 2009
pp. 678-681
A hybrid system of Case Based Reasoning (CBR) with Fuzzy ARTMAP (FAM) has been proposed to perform fault diagnosis for actuator system in DAMADICS benchmark. The hybrid system of CBR and FAM is for undertaking the stability plasticity dilemma for the incre...
 
Analog Multiplier with High Accuracy
Found in: Computational Intelligence, Communication Systems and Networks, International Conference on
By K. Diwakar, C. Senthilpari, Ajay Kumar Singh, Lim Way Soong
Issue Date:July 2009
pp. 62-66
In this paper, a new technique is proposed for multiplication of two sampled analog signals and the output is in digital form. One analog signal is fed to the input of Delta sigma modulator (DSM1) after sampling. The sampled output of the second analog sig...
 
Credibility: How Agents Can Handle Unfair Third-Party Testimonies in Computational Trust Models
Found in: IEEE Transactions on Knowledge and Data Engineering
By Jianshu Weng, Zhiqi Shen, Chunyan Miao, Angela Goh Eck Soong, Cyril Leung
Issue Date:September 2010
pp. 1286-1298
Usually, agents within multiagent systems represent different stakeholders that have their own distinct and sometimes conflicting interests and objectives. They would behave in such a way so as to achieve their own objectives, even at the cost of others. T...
 
Improved prosody generation by maximizing joint likelihood of state and longer units
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Yao Qian, Zhizheng Wu, Frank K. Soong
Issue Date:April 2009
pp. 3781-3784
The current state-of-art HMM-bsed TTS can produce highly intelligible output speech and deliver a decent segmental quality. However, its prosody, especially at the phrase or sentence level, tends to be bland. The blandness of synthesized prosody is partial...
 
State mapping for cross-language speaker adaptation in TTS
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Yi-Ning Chen, Yang Jiao, Yao Qian, Frank K. Soong
Issue Date:April 2009
pp. 4273-4276
Cross-language speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-language speaker adaptation, a common phoneme set, assumed to be used by different speakers of the same language, does not exist any l...
 
An evidence framework for Bayesian learning of continuous-density hidden Markov models
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Yu Zhang, Peng Liu, Jen-Tzung Chien, Frank Soong
Issue Date:April 2009
pp. 3857-3860
We present an evidence Bayesian framework, which can learn both the prior distributions and posterior distributions from data, for continuous-density hidden Markov models (CDHMM). The goal of this study is to build the regularized CDHMMs to improve model g...
 
Improving mispronunciation detection using machine learning
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Yuqiang Chen, Chao Huang, Frank Soong
Issue Date:April 2009
pp. 4865-4868
In this paper, we investigate the problem of mispronunciation detection by considering the influence of speaker and syllables. Machine learning techniques are used to make our method more convenient and flexible for new features, such as syllables normaliz...
 
An Effective Surveillance System Using Thermal Camera
Found in: Signal Acquisition and Processing, International Conference on
By Wai Kit Wong, Poi Ngee Tan, Chu Kiong Loo, Way Soong Lim
Issue Date:April 2009
pp. 13-17
Thermography, or thermal visualization is a type of infrared visualization. Thermographic cameras are used in many heavy factories like metal recycling factories, wafer production factories and etc for monitoring the temperature conditions of the machines....
 
An NGN Convergence Service, U-ID Based EDS, for Multiple Service Provider Environments
Found in: Convergence Information Technology, International Conference on
By Soong-Hee Lee, Sok-Pal Cho, Hee-Chang Chung, Byung-Ik Choi, Sun-Moo Kang, Yeong-Ro Lee, Dong-Il Kim, Seung-Kun Lee, Jong-Wook Jang
Issue Date:November 2008
pp. 718-727
Considerations for multiple network and service provider environments are regarded as essential for the successful deployment of convergence services in NGN. Event driven service (EDS) is regarded as a typical convergence service converging different funct...
 
Version Management Using Demand-Based Tree for Replicas Consistency in Grid Database
Found in: Advanced Language Processing and Web Information Technology, International Conference on
By Soong-Sun Shin, Dong-Wook Lee, Sung-Ha Baek, Gyoung-Bae Kim, Hae-Young Bae
Issue Date:July 2008
pp. 324-332
The grid database management system is used for large data processing, high availability and data integration by grid environment. It has a replica for processing performance and high availability in each node. The grid database has a problem of inconsiste...
 
A Context Model for B2B Collaborations
Found in: Services Computing, IEEE International Conference on
By Tan Puay Siew, Angela Goh Eck Soong, Stephen Lee Siang Guan
Issue Date:July 2008
pp. 108-115
Context-awareness (CA) has been applied in different domains, particularly in ubiquitous computing, to provide better value-added services. CA has also been used, albeit sporadically, in business related applications. This paper discusses an on-going resea...
 
FuzMOD: A Fuzzy Multi-ontology Web Service Discovery System
Found in: Asia-Pacific Conference on Services Computing. 2006 IEEE
By Duy Ngan Le, Angela Eck Soong Goh
Issue Date:December 2007
pp. 197-203
The future of e-business is closely related to recent developments in web services. The rapid development of web services has led to a demand for a web service discovery mechanism. Though such discovery systems have been developed, there is a lack of suppo...
 
Current Practices in Measuring Ontological Concept Similarity
Found in: Semantics, Knowledge and Grid, International Conference on
By Duy Ngan Le, Angela Eck Soong Goh
Issue Date:October 2007
pp. 266-269
Ontologies are widely used and play important roles in applications related to knowledge management, artificial intelligence, natural language processing, etc. Measuring the semantic similarity between ontological concepts is necessary in applications that...
 
Minimum Error Discriminative Training for Radical-Based Online Chinese Handwriting Recognition
Found in: Document Analysis and Recognition, International Conference on
By Y. Zhang, P. Liu, F. Soong
Issue Date:September 2007
pp. 53-57
Free style Chinese handwriting recognition continues to pose a challenge to researchers due to the variety of writing styles. To recognize handwritten characters in an online mode, Hidden Markov Model (HMM) has been naturally adopted to model the pen traje...
 
A MSD-HMM Approach to Pen Trajectory Modeling for Online Handwriting Recognition
Found in: Document Analysis and Recognition, International Conference on
By L. Ma, F. Soong, P. Liu, Y.-J. Wu
Issue Date:September 2007
pp. 128-132
In modeling online handwritten characters, imaginary strokes have been conveniently generated by connecting ad- jacent real strokes together to form a continuous trajectory. However, this approach causes confusions among charac- ters with similar but actua...
 
Word graph based speech rcognition error correction by handwriting input
Found in: Proceedings of the 8th international conference on Multimodal interfaces (ICMI '06)
By Frank K. Soong, Peng Liu
Issue Date:November 2006
pp. 339-346
We propose a convenient handwriting user interface for correcting speech recognition errors efficiently. Via the proposed hand-marked correction on the displayed recognition result, substitution, deletion and insertion errors can be corrected efficiently b...
     
Closed form solution for QoS: constrained information--theoretic sum capacity of reverse link CDMA systems
Found in: Proceedings of the 2nd ACM international workshop on Quality of service & security for wireless and mobile networks (Q2SWinet '06)
By Anthony C. K. Soong, Arash Abadpour, Attahiru Sule Alfa
Issue Date:October 2006
pp. 123-128
The information-theoretic maximum system capacity in a CDMA network, which guarantees fairness to mobile stations,can be achieved by optimally allocating transmit powers to the mobile stations while imposing individual QoS constraints. Even though this opt...
     
A Study of Shared Buffer Memory Segmentation for Packet Switched Networks
Found in: Advanced International Conference on Telecommunications / Internet and Web Applications and Services, International Conference on
By Stephen O'Kane, Sakir Sezer, Lum Soong Lit
Issue Date:February 2006
pp. 55
Classical shared buffer architectures are designed for variable sized packets and deploy memory segmentation for efficient resource management and to overcome memory fragmentation. There subsequently exists a tradeoff in selecting the most appropriate segm...
 
Interference Distribution in the Nakagami FadingWireless CDMA Ad Hoc Networks with Multi-Code Multi-Packet Transmission (MCMPT)
Found in: Local Computer Networks, Annual IEEE Conference on
By Lili Zhang, Boon-Hee Soong
Issue Date:November 2005
pp. 84-90
<p>In this paper, we derive the distribution of Multiple Access Interference (MAI) power for wireless Code Division Multiple Access (CDMA) ad hoc networks operating in a general Nakagami-m fading channel model. Furthermore, we propose a Multi-Code Mu...
 
Technological Enablers of the IEEE Wireless Metropolitan Area Network (IEEE 802.16)
Found in: Quality of Service in Heterogeneous Wired/Wireless Networks, International Conference on
By Anthony C. K. Soong
Issue Date:August 2005
pp. xxiii
<p>There has been keen interest in the literature recently on the IEEE wireless metropolitan area network (MAN) developed within IEEE 802.16. Through the use of flexible physical layer features and medium access control (MAC) layer mechanisms, this s...
   
Overhead Analysis of Location-Aware Two-Phase Coding Multi-Channel MAC Protocol (LA-TPCMMP) for MANETs
Found in: Local Computer Networks, Annual IEEE Conference on
By Lili Zhang, Boon-Hee Soong, Wendong Xiao
Issue Date:November 2004
pp. 164-171
In this paper, we present a novel location-aware multi-channel Medium Access Control (MAC) protocol for large-scale dense Mobile Ad Hoc Networks (MANETs) based on a scalable two-phase coding scheme, where the first-phase code is used for differentiating ad...
 
Derivation and Analysis of Fragment Libraries of Protein Structures
Found in: Bioinformatic and Bioengineering, IEEE International Symposium on
By In-Yee Lee, Ta-Tsen Soong, Jan-Ming Ho, Ming-Jing Hwang
Issue Date:May 2004
pp. 516
Fragment assembly is attracting intense research interest as a means of predicting protein structure from sequences. Success requires a good library of local structures (i.e. fragments) to serve as building blocks for whole protein reconstruction. Here, we...
 
Multirate adaptive filtering for immersive audio
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Jong-soong Lim, C. Kyriakakis
Issue Date:May 2001
pp. 3357-3360
This paper describes a method for implementing immersive audio rendering filters for single or multiple listeners and loudspeakers. In particular, the paper is focused on the case of single or two listeners with different loudspeaker arrays to determine th...
 
Hierarchical stochastic feature matching for robust speech recognition
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Hui Jiang, F. Soong, Chin-Hui Lee
Issue Date:May 2001
pp. 217-220
In this paper we investigate how to improve the robustness of a speech recognizer in a noisy, mismatched environment when only a single or a few test utterances are available for compensating the mismatch. A new hierarchical tree-based transformation is pr...
 
Two-step backup mechanism for real-time main memory database recovery
Found in: Real-Time Computing Systems and Applications, International Workshop on
By Mi-Seon Choi, Hye-Sook Yoon, Eun-Mi Song, Young-Keol Kim, Young-Kuk Kim, Soong-Il Jin, Mi-Kyong Han, Wan Choi
Issue Date:December 2000
pp. 453
Proposes a recovery mechanism for real-time main-memory database systems (RT-MMDBSs) which aims at reducing the system recovery time, as well as ensuring a fast response time and predictability. Conventional main-memory database (MMDB) recovery schemes usu...
 
Effect of genetic algorithm parameters on PCS network planning
Found in: Local Computer Networks, Annual IEEE Conference on
By Juan Li, Yong Liang Guan, Boon Hee Soong
Issue Date:November 2000
pp. 400
A study on the effect of genetic parameters is carried out in order to find the optimum value of the parameters in genetic algorithms for solving personal communication service network planning problems. As for any genetic algorithm, one of the problems is...
 
An Efficient Rule-Based OPC Approach Using a DRC Tool for 0.18?m ASIC
Found in: Quality Electronic Design, International Symposium on
By Ji-Soong Park, Chul-Hong Park, Sang-Uhk Rhie, Yoo-Hyon Kim, Moon-Hyun Yoo, Jeong-Taek Kong, Hyung-Woo Kim, Sun-Il Yoo
Issue Date:March 2000
pp. 81
The increasing complexity and data volume of VLSI designs demand an efficient optical proximity correction (OPC) technique. In this paper, we address the issues related to the gate bridge, which is serious in the sub-quarter micron technology, and the wide...
 
Interconnect Delay Fault Testing with IEEE 1149.1
Found in: Test Conference, International
By Yuejian Wu, Paul Soong
Issue Date:September 1999
pp. 449
No summary available.
 
A block least squares approach to acoustic echo cancellation
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By E. Woudenberg, F.K. Soong, B.-H. Juang
Issue Date:March 1999
pp. 869-872
We propose an efficient block least squares (BLS) algorithm for acoustic echo cancellation. The high computation and memory requirements associated with a long room echo make the simple, gradient-based LMS filter a more acceptable commercial solution than ...
 
Hidden Markov models with divergence based vector quantized variances
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By J. Kim, R. Haimi-Cohen, F. Soonge
Issue Date:March 1999
pp. 125-128
This paper describes a method to significantly reduce the complexity of continuous density HMM with only a small degradation in performance. The proposed method is noise-robust and may perform even better than the standard algorithm if training and testing...
 
ABR Service Provision in Ethernet-ATM Internetworking
Found in: Information Networking, International Conference on
By Hun Kang, Soong-Hee Lee
Issue Date:January 1998
pp. 0661
Abstract: Ethernet users can access resources in ATM networks efficiently through Ethernet-ATM internetworking with ABR service. We survey several issues for implementing ABR service in Ethernet-ATM inter-networking and propose a structure for end-to-end f...
 
Multipath time delay estimation using higher order statistics
Found in: Signal Processing Workshop on High-Order Statistics, IEEE
By Ying-Chang Liang, A.R. Leyman, Boon-Hee Soong
Issue Date:July 1997
pp. 0009
Abstract: This paper addresses the problem of time delay estimation (TDE) in spatially correlated noises. Two cases are considered: (i) TDE of non-Gaussian signal in spatially correlated Gaussian noises; and (ii) TDE of Gaussian signal in spatially correla...
 
Generalized Mixture of HMMs for Continuous Speech Recognition
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By F. Korkmazskiy, B. Juang, F. Soong
Issue Date:April 1997
pp. 1443
No summary available.
 
A reactive access control scheme at UNI for congestion control in ATM-based B-ISDN
Found in: Local Computer Networks, Annual IEEE Conference on
By Soong Hee Lee
Issue Date:November 1996
pp. 366
A reactive access control scheme, which controls effectively B-ISDN congestion, is proposed. The increasing number of active traffic sources results in increasing amount of feedback traffic in the current congestion control schemes. The proposed scheme res...
 
High-accuracy connected digit recognition for mobile applications
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By S.K. Gupta, F. Soong, R. Haimi-Cohen
Issue Date:May 1996
pp. 57-60
We present a connected digit recognition system with low storage and computational complexity which achieves good performance in car noise. Our system uses the TI-DIGITS database with additive car noise for training whole-word digit and background models. ...
 
An orthogonal polynomial representation of speech signals and its probabilistic model for text independent speaker verification
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Chi-Shi Liu, Hsiao-Chuan Wang, F.K. Soong, Chao-Shih Huang
Issue Date:May 1995
pp. 345-348
A segmental probabilistic model based on an orthogonal polynomial representation of speech signals is proposed. Unlike the conventional frame based probabilistic model, this segment based model concatenates the similar acoustic characteristics of consecuti...
 
Large vocabulary word recognition based on tree-trellis search
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Jung-Kuei Chen, F.K. Soong, Lin-Shan Lee
Issue Date:April 1994
pp. 137-140
In this paper we propose a large vocabulary (90000 words), Chinese (Mandarin) word recognizer based on the tree-trellis fast search algorithm. The recognizer is divided into 3 modules: local likelihood computation, a forward trellis search and a backward t...
 
Discriminative training of high performance speech recognizer using N best candidates
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Jung-Kuei Chen, F.K. Soong
Issue Date:April 1994
pp. 625-628
Proposes an N-best candidates based, discriminative training procedure for constructing high performance HMM speech recognizers. The algorithm has two features: (1) a new frame-level loss function; (2) N best candidates are used for training. The new frame...
 
Continuous probabilistic acoustic map for speaker identification
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By B.L. Tseng, F.K. Soong, A.E. Rosenberg
Issue Date:March 1992
pp. 161-164
A continuous probabilistic acoustic map (CPAM) approach to speaker recognition is investigated. In the CPAM formulation, the speech input of a speaker is parameterized as a mixture of tied, universal probability density functions (PDFs) with either a CPAM ...
 
A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By F.K. Soong, E.-F. Huang
Issue Date:April 1991
pp. 705-708
A novel tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition is presented. The search consists of a forward time-synchronous trellis search and a backward time-asynchronous tree search. The Viterbi algo...
 
Blueprints for the computer city: The quest for an architect's computer
Found in: Proceedings of the 1984 annual conference of the ACM on The fifth generation challenge (ACM 84)
By Charles Atwood, Charles Eastman, Douglas Stoker, Norman Soong, William Mitchell
Issue Date:January 1984
pp. 303-304
This panel session is supported by the American Institute of Architects, the AIA. The purpose of this panel is to publicize the computing needs of the building industry, which consists primarily of architects, engineers, and contractors. We thank the AIA C...
     
One-dimensional optimization on multiprocessor systems
Found in: IEEE Transactions on Computers
By Mark A. Franklin,Norman L. Soong
Issue Date:January 1981
pp. 61-66
This paper presents a straightforward approach to determining how best to utilize an MIMD multiprocessor in the solution of one-dimensional optimization problems involving continuous unimodal functions and nongradient search techniques. A methodology is pr...
   
A program stability measure
Found in: Proceedings of the 1977 annual conference (ACM 77)
By Norman Loongsung Soong
Issue Date:January 1977
pp. 163-173
This paper contributes to the understanding of program structures in terms of its stability and reliability in a quantitative sense. Distinctions are made between the logical structure of a program and the information structure of a program. The general ch...
     
 1  2 Next >>