Session Index - ISCSLP 2002

Keynote speeches

Keynote Speech I:
Application of Speech Technology to the Assistance of Speech and Auditory Training
Hsiao-Chuan WANG, National Tsing Hua University, Hsinchu

Keynote Speech II:
Convergence of Statistical and Rule-based approach in Multilingual Speech Translation
XU Bo, Chinese Academy of Sciences, Beijing


Invited Talks

The Inhomogeneous Hidden Markov Models and its Training and Recognition Algorithms of Speech Recognition
Speaker: WANG Zuoying, Tsinghua University, Beijing

Concatenative Chinese Speech Synthesis and Quality Evaluation
Speaker: LI Haizhou Infotalk Corporation, Singapore

Intelligent Speech for Information Systems (ISIS): A Multi-modal, Trilingual, Distributed Conversational System with Combined Interaction and Delegation Dialogs
Speaker: Helen MENG, The Chinese University of Hong Kong, Hong Kong

Challenges and Advances in Semantic Representation and Interpretation
Speaker: Jhing-Fa WANG, National Cheng Kung University, Tainan


Totorials

Tutorial I
Information Retrieval Techniques for Spoken Language Processing

Lee-Feng Chien
Institute of Information Science Institute of Information Science, Academia Academia Sinica Sinica, Taiwan , Taiwan

Tutorial II
Speech Recognition, Understanding and Dialog Modeling
Kuansan Wang
Microsoft Research


Session O1A-Speech Recognition (Oral)   

O1A.01. A Generalized Common Vector Approach for Robust Speaker Independent Automatic Speech Recognition
Der-Jenq LIU and Chin-Teng LIN, National Chiao-Tung University, Hsinchu

O1A.02. A Super Phonetic System and Multi-Dialect Chinese Speech Corpus for Speech Recognition
Yiqing ZU, Yingzhi CHEN, Yaxin ZHANG, Motorola China Research Center, Shanghai; Lei ZHOU, Ming SHEN, The Institute of Linguistics Chinese Academy of Social Sciences, Beijing; Jingjing HUANG, East China Normal university, Shanghai

O1A.03. Acoustic Model Comparison for an Embedded Phoneme-based Mandarin Name Dialing System
ZHU Xuan, WANG Rui, CHEN Yining, LIU Jia, LIU Run-Sheng, Tsinghua University, Beijing

O1A.04. Improving performance of telephone-based Mandarin speech recognition
Huayun ZHANG, Bo XU, Taiyi HUANG, Chinese Academy of Sciences, Beijing

O1A.05. Comparative Study of Linear Feature Transformation Techniques for Mandarin Digit String Recognition
Jian SHAN, Yuanyuan SHI, Jia LIU, Runsheng LIU, Tsinghua University, Beijing


Session O1B-Speech Synthesis (Oral)   

O1B.01. A Statistical Model with Hierarchical Structure for Predicting Prosody in a Mandarin Text-to-Speech System
Ming-Shing YU, Neng-Huang PAN, Ming-Jer WU, National Chung-Hsing University,Taichung

O1B.02. Concatenative Mandarin TTS Accommodating Isolated English Words
Zhenli YU, Dongjian YUE, Jian-Cheng HUANG, Motorola China Research Center, Shanghai

O1B.03. An NN-based Approach to Prosody Generation for English Word Spelling in English-Chinese Bilingual TTS
Wei-Chih KUO, Yih-Ru WANG, Hung-Mao LU, Sin-Horng CHEN, Chiao Tung University, Hsinchu

O1B.04. Automatic Stress Prediction of Chinese Speech Synthesis
Jian-Hua TAO, Sheng ZHAO, Lian-Hong CAI, Tsinghua University, Beijing

O1B.05. Study on Framework for Chinese Pronunciation Variation Modeling
LI Jing, XU Mingxing and WU Wenhu, Tsinghua University, Beijing


Session O2A- Multimedia Retrieval and Applications (Oral)

O2A.01. Towards Retrieval of Video Archives Based on the Speech Content
Mei-fang HUANG, Kuan-ting CHEN and Hsin-min WANG, Academia Sinica, Taipei

O2A.02. Automatic Taxonomy Generation for Speech Archives
Lee-Feng CHIEN, Chien-Chung HUANG, Jei-Wen TENG, Shui-Lung CHUANG, Academia Sinica, Taipei

O2A.03. A Data-driven Indexing Approach for Chinese Spoken Document Retrieval
Chun-Jen WANG, Berlin CHEN, Lin-shan LEE, National Taiwan University, Taipei

O2A.04. Multi-Speaker Dialogue for Mobile Information Retrieval
Hsien-Chang WANG, Chieh-Yi HUANG, Chung-Hsien YANG , Jhing-Fa WANG, National Cheng-Kung University, Tainan

O2A.05. On the construction of a VoiceXML Voice Browser
Chih-Hsing HSU, Miaw-Ru HSU, Cher-Yao YANG, Sen-Chia CHANG, Industrial Technology Research Institute (ITRI), Hsinchu


Session O2B- Speaker/Emotion Recognition and Applications (Oral)
  
O2B.01. Hybrid Text-Independent Speaker Recognition Using Character-Based Background HMMs and GMMs for Mandarin Speech
DENG Hao-jiang, DU Li-min, WAN Hong-jie, Chinese Academy of Sciences,Beijing

O2B.02. An improvement of the GMM Speaker Identification Method by Using Two-state HMM and Discriminative Training
Yih-Ru WANG, and Shin-Ming FAN, National Chiao Tung University, Hsinchu

O2B.03. Emotion Recognition via Acoustic Features and Semantic Contents in Speech
Ze-Jing CHUANG and Chung-Hsien WU, National Cheng Kung University, Tainan

O2B.04. Rapid Prototyping an Operator Assisted Call Routing System
Chun-Jen LEE, Jason S. CHANG, Chunghwa Telecom Co., Ltd. Chung-Li

O2B.05. Efficient Phone Based Recognition Engines for Chinese and English Isolated Command Applications
Xavier MENENDEZ-PIDAL, Lei DUAN, Jingwen LU, Beatriz DUKES, Mike EMONTS, Gustavo HERNANDEZ ABREGO, Lex Lorenshaw, Spoken Language Technology Group, SONY NSCA, San Jose, California


Session P1A- Speech/Speaker Recognition and Applications (Poster)
 
P1A.01. Time-Frequency Distributions of Spectrum Energy Operator in Large Vocabulary Mandarin Speaker Independent Speech Recognition System
Fadhil H. T. AL-DULAIMY, Zuoying WANG, Tsinghua University, Beijing

P1A.02. Dynamic and Goal-oriented Interaction for Multi-modal Service Agents
Tommy SHEU, Bor-Shen LIN, Institute for Information Industry, Taipei

P1A.03. Testing the Hypothesis of Multivariate Normality in Bayesian Approaches to Speaker Adaptation
Li-Wei WANG, Zuo-Ying WANG, Tsinghua University, Beijing

P1A.04. Incorporating Probability into Support Vector Machine for Speaker Recognition
Tieyan FU, Qixiu HU, XU Guangyou, Tsinghua University, Beijing

P1A.05. Comparisons of MLLR and CDCN for Speech Recognition in Additive Noise by Experiments
Guo-Hong DING, Chengrong LI and Bo XU, Chinese Academy of Sciences, Beijing

P1A.06. The Efficient PMC for Robust Speech Recognition in Noisy Environments
Cailian MIAO, Yang Sheng WANG, Chinese Academy of Sciences, Beijing

P1A.07. Enhancing the Stability of Speaker Verification with Compressed Templates
WEN Xue, LIU Runsheng, Tsinghua University, Beijing


Session P1B- Speech Analysis (Poster)

P1B.01. Speech Detection Based on Discrete Wavelet Transform
Ching-Tang HSIEH, Tamkang University, Taipei, Chih-Hsu HSU, Dahan Institute of Technology, Hua-Lien

P1B.02. Pitch Declination in the Statement Sentence in Mandarin
WANG Anhong, LU Shinan, CHEN Ming, Department of Chinese, Peking University; Institute of Acoustics, Academia Sinica; Beijing InfoQuick SinoVoice Speech Technology, Beijing

P1B.03. Research on the Semivowel by Dynamic Palatogram in Standard Chinese
ZHENG Yuling, BAO Huaiqiao, Nationality Studies, CASS, Beijing

P1B.04. Acoustical F0 Analysis of Continuous Cantonese Speech
Yujia li, Tan LEE and Yao QIAN, The Chinese University of Hong Kong, Hong Kong

P1B.05. An Improved Entropy-based Endpoint Detection Algorithm
Chuan JIA, Bo XU, Chinese Academy of Sciences, Beijing

P1B.06. Robust Speech Detection with Heteroscedastic Discriminant Analysis Applied to the Time-Frequency Energy
Ye TIAN, Zuoying WANG, and Dajin LU, Tsinghua University, Beijing


Session P1C- Feature Extraction (Poster)
 
P1C.01. A New Normalization for MFCC: Multi Layer Strategy and Rrcursive Progress
WANG Dong; ZHU Xiaoyan; LIU Ying, Tsinghua University, Beijing

P1C.02. A Pitch Detection Algorithm Based on Special Points and Area
Li WANG, Xin LV, Tie-Jun ZHAO, Zhan-Yi LIU, Harbin Institute of Technology, Harbin

P1C.03. An algorithm for Voiced / Unvoiced Decision and Pitch Estimation in Speech Feature Extraction
WANG Dong, CHEN Yi-Ning, LIU Jia, Tsinghua University, Beijing

P1C.04. Comparison between the Spectral Estimation Techniques by Different Spectral-distortion Measures
ZHU Shaohui, Wenju LIU, Bo XU, Chinese Academy of Sciences, Beijing

P1C.05. Accuracy Improving Method for Parametric Trajectory Modeling and Its Use in A* Search
Yi-yan ZHANG, Wen-ju LIU, Bo XU, Chinese Academy of Sciences, Beijing

P1C.06. Some Issues on the Study of Vocal Tract Normalization
Zhuo WANG, Peng DING, Bo XU, Chinese Academy of Sciences, Beijing

P1C.07. Compact Speech Features Based on Wavelet Transform and PCA with Application to Speaker Identification
Ching-Tang HSIEH, Eugene LAI, Wan-Chen CHEN, You-Chuang WAN, Tamkang University, Taipei


Session O3A-Speech Analysis & Recognition (Oral)

O3A.01. Distributed Mandarin Speech Recognition under Wireless Environment
Cheng-Huang WU, Yumin LEE, and Lin-shan LEE, National Taiwan University, Taipei

O3A.02. Optimization of Viterbi Beam Search in Speech Recognition
Jyh-Shing Roger JANG, Shiuan-Sung LIN, National Tsing Hua University, Taipei

O3A.03. A Voice Activity Detection Algorithm Based on Perceptual Wavelet Packet Transform and Teager Energy Operator
Jhing-Fa WANG and Shi-Huang CHEN, National Cheng Kung University, Tainan

O3A.04. Speech Enhancement Using Wavelet Transform with Constrained Thresholds
Ching-Ta LU, Hsiao-Chuan WANG, National Tsing Hua University, Hsinchu

O3A.05. Constrained Maximum A Posteriori Approach for Speech Enhancement
Chuan JIA, Jian ZHANG, Bo XU, Chinese Academy of Sciences, Beijing


Session O3B- Natural Language Processing (Oral)
 
O3B.01. Knowledge-based Sense Pruning Using the HowNet: An Alternative to Word Sense Disambiguation
GAN Kok-Wee, WANG Chi-Yung, Brian MAK, Hong Kong University of Science and Technology, Hong Kong

O3B.02. Equivalent Node-Based Speech Grammar Optimization
Min ZHANG, Cuntai GUAN, Haizhou LI, Infotalk Technology, Singapore

O3B.03. Linguistic and Acoustic Analysis of Chinese Person Names
Wen-Jie CAO, Bo XU, Juha ISO-SIPILA*, Chinese Academy of Sciences; *Nokia China R&D Center, Beijing

O3B.04. Improvements on a Belief Network Framework for Natural Language Understanding of Domain-Specific Chinese Queries
Bonnie MOK and Helen M. MENG, The Chinese University of Hong Kong, Hong Kong

O3B.05. Automatic Construction of English-Chinese Translation Lexicon from Parallel Spoken Language Corpus
Bo-xing CHEN, Li-min DU, Chinese Academy of Sciences, Beijing


Session P2A-Speech Recognition (Poster)
 
P2A.01. Improvement of the Post-processing Method for Isolated Word Oov Rejection
Yifei ZHU,Chengrong LI,Bo XU, Chinese Academy of Science, Beijing

P2A.02. Real-time Viterbi Searching for Practical Telephone Speech Recognition Systems
Jin ZHANG, Jia LIU, Run-Sheng LIU, Tsinghua University, Beijing

P2A.03. Two-Pass Continuous Digit String Decoder
WANG Zhi-yu, WEN Yuan, LI Ming, Chinese Academy of Sciences, Beijing

P2A.04. Partial Change Phone Models for Pronunciation Variations in Spontaneous Mandarin Speech
LIU Yi, Pascale FUNG, University of Science and Technology, Hong Kong

P2A.05. Likelihood Probability Mismatch Analysis and Normalization in Multilingual Speech Applications
Bin MA, Cuntai GUAN, Haizhou LI, InfoTalk Technology, Singapore

P2A.06. Comparison and Combination of Confidence Measures in Isolated Word Recognition
XIONG Zhenyu, XU Mingxing, WU Wenhu, Tsinghua University, Beijing

P2A.07. Confidence Measures for Large Vocabulary Continuous Speech Recognition
LV Ping, WANG Zuo-Ying, LU Da-Jin, Tsinghua University, Beijing

P2A.08. A Comparative Study on Wavelet Packet Based Front-End in Connected Mandarin Digit Recognition
Xiu Ping WANG, Chuan-Qi ZHU, Zong-Ge LI, Fudan University, Shanghai

P2A.09. Study on the Strategy for Hierarchical Speech Recognition
Dali YANG, Mingxing XU and Wenhu WU, Tsinghua University, Beijing

P2A.10. Fast Likelihood Computation Method Using Block-Diagonal Covariance Matrices in Hidden Markov Model
Rui WANG, Xuan ZHU, Yining CHEN, Jia LIU, Runsheng LIU, Tsinghua University, Beijing

P2A.11. Integration of Tone Related Feature for Mandarin Speech Recognition by a One-Pass Search Algorithm
WONG Pui-Fung, Man-Hung SIU, Hong Kong University of Science and Technology, Hong Kong


Session P2B-Speech Synthesis (Poster)

P2B.01. Applying Source-filter Model in Chinese Speech Synthesis
YI Lifu, TIAN Jing, SUN Jingcheng, Chinese Academy of Sciences, Institute of Acoustics, Beijing

P2B.02. An Efficient Way to Learn Rules for Grapheme-to-Phoneme Conversion in Chinese
Zi-rong ZHANG, Min CHU, Eric CHANG, Microsoft Research Asia, Beijing

P2B.03. Modeling Duration and Intonation in Mandarin Chinese Synthesis with a Neural Network
Hongwei DING, Oliver JOKISCH, Hans KRUSCHKE, Dresden University of Technology, Germany

P2B.04. Hakka Pitch-Contour Parameter Generation Using a Mandarin-Trained Pitch-Contour Model
Hung-Yan GU and Shiue-Jen LI, National Taiwan University of Science and Technology, Taipei

P2B.05. Large lexicon construction for TTS system
Ben-Feng CHEN, Guo-Ping HU, Ren-Hua WANG, University of Science & Technology of China, Hefei

P2B.06. Decision Tree Based Unit Pre-Selection in Mandarin Chinese Synthesis
Zhen-Hua LING, Yu HU, Zhi-Wei SHUANG, Ren-Hua WANG, University of Science and Technology, Hefei

P2B.07. Study on Detection of Prosodic Phrase Boundaries in Spontaneous Speech
Hui SUN, Mingxing XU, Wenhu WU, Tsinghua University, Beijing

P2B.08. Design of Embedded Application Oriented Distributed Speech Synthesis System with High Naturalness
TANG Hao, YIN Bo, and Ren-Hua WANG, University of Science and Technology of China, Hefei

P2B.09. A Novel Approach for Pitch Modification on Time Domain
LI Ming, WANG Zhiyu, WEN Yuan, HOU Zhen, YU Tiecheng, Chinese Academy of Sciences, Beijing

P2B.10. Prosodic Phrase Detection for Chinese TTS using CART and Statistical Model
DONG Minghui LUA Kim-Teng, National University of Singapore, Singapore

P2B.11. Voice Quality Analysis under the Pitch Effect
Dan-Ning JIANG, Jian-Hua TAO, Lian-Hong CAI, Tsinghua University, Beijing


Session P2C- Spoken Dialogue and Natural Language Processing (Poster)

P2C.01. Improving Language Modeling by Combining Heteogeneous Corpora
Zheng-Yu ZHOU, Fudan University, Shanghai; Jian-Feng GAO, Eric CHANG, Microsoft Research Asia, Beijing

P2C.02. PhoneAgent: A Conversational Interface for Telephone Exchange System
Bin SHE, Mingxing XU, Wenhu WU, Tsinghua University, Beijing

P2C.03. The Design of a Multi-Domain Chinese Dialogue System
Wei-Tek HSU, Huei-Ming WANG, Yi-Chun LIN, Industrial Technology Research Institute, Hsinchu

P2C.04. A Spoken Dialogue Model Based on Extended Lambek Calculus
Ke-Song HAN, Gui-Lin CHEN, Motorola Labs, China Research Center, Shanghai

P2C.05. Preparing for Evaluation of a Flight Spoken Dialogue System
Xiaojun WU, Mingxing XU, and Wenhu WU, Tsinghua University, Beijing

P2C.06. An Automatic Speech Recognition Strategy Directed by the Semantic Knowledge in Dialogue System
Guoliang ZHANG, Pengju YAN, Mingxing XU and Wenhu WU, Tsinghua University, Beijing

P2C.07. Developing Chinese TAK for Computer Directly
Guo-Ping HU, Ben-Feng CHEN, Ren-Hua WANG, University of Science and Technology of China, Hefei

P2C.08. An Approach to Automatic Identification of Chinese Base Noun Phrases
Yan ZHANG, Chengqing ZONG and Bo XU, Chinese Academy of Sciences, Beijing

P2C.09. Chinese Person Name Identification Based on Rules and Statistics
Wenjie CAO, Chengqing ZONG, Chinese Academy of Sciences, Beijing; Juha ISO-SIPILA , Nokia China R&D Center, Beijing; Bo XU, Chinese Academy of Sciences, Beijing

P2C.10. Investigation and Analysis on Designing Chinese Balance Corpus
Rile HU, Chengqing ZONG, Chinese Academy of Sciences, Beijing; Juha ISO-SIPILA , Nokia China R&D Center, Beijing; Bo XU, Chinese Academy of Sciences, Beijing

P2C.11. A Compression Method Used in Language Modeling for Handheld Devices
Genqing WU, Fang ZHENG, Wenhu WU, Tsinghua University, Beijing

P2C.12. Spoken Language Identification Using Bigram
CHENG Xuelin, WU Kaizheng, WANG Han, LI Zongge, Fudan University, Shanghai


Session O4A- Speech recognition and Adaptation (Oral)
 
O4A.01. A Comparative Study of Several Incremental Adaptation Algorithms for Speaker Adaptation
Bin MA InfoTalk Technology Pte Ltd, Singapore; Qiang HUO, The University of Hong Kong, Hong Kong

O4A.02. Structure-Based Compensation Using an Improved Statistical Linear Approximation for Mandarin Speech Recognition over Telephone
Zhao-Bing HAN, Hua-Yun ZHANG, Bo XU, Chinese Academy of Sciences, Beijing

O4A.03. A Comparative Study of Quickprop and GPD Optimization Algorithms for MCELR Adaptation of CDHMM Parameters
Jian WU and Qiang HUO, The University of Hong Kong, Hong Kong

O4A.04. Integration of Model Adaptation and Missing Feature Theory for Robust Speech Recognition
An-Tze YU and Hsiao-Chuan WANG, Tsing Hua University, Hsinchu

O4A.05. An Investigation on Wireless Speech Recognition by Data Contamination and Robust Training Techniques
Wei-Tyng HONG and Ke-Shiu CHEN, Industrial Technology Research Institute, Hsinchu


Session O4B- Speech Synthesis (Oral)
   
O4B.01. The Effect of Tonal Context on Cantonese Concatenative Speech Synthesis
Tien-Ying FUNG and Helen M. MENG, The Chinese University of Hong Kong, Hong Kong

O4B.02. Face Synthesis Driven by Audio Speech Input Based on HMMs
Ling SUN, Wei LAI, Ren-Hua WANG, University of Science & Technology of China, Heifei

O4B.03. Annotation of Chinese Prosodic Level Based on Probabilistic Model
Rui CAI*, Zhi-Yong WU, Lian-Hong CAI, Tsinghua University, Beijing

O4B.04. A Cross-linguistic Study on Discourse and Syntactic Boundary Cues in Spontaneous Speech: Using Duration as an Example
Janice FON, National Taiwan Normal University, Taipei

O4B.05. A Study of Evaluation Method for Synthetic Mandarin Speech
BAO Huaiqiao, Institute of Nationality Studies, CASS, Beijing; WANG Anhong, Department of Chinese, Peking University, Beijing; LU Shinan, Institute of Acoustics, Academia Sinica, Beijing