|
ISCA ArchiveInternational Symposium on Chinese Spoken Language Processing (ISCSLP 2004)The Chinese University of Hong Kong, Hong Kong
| 
|
Bibliographic Reference
[ISCSLP 2004] International Symposium on Chinese Spoken Language Processing (ISCSLP 2004), The Chinese University of Hong Kong, Hong Kong, December 15-18, ISCA Archive, http://www.isca-speech.org/archive_open/iscslp2004/index.html
Author Index
BAI Junmei L3.6 BAI Yanning P1.9 BAILLY Garard P1.15 BAOTable of Contents
KEYNOTE-1: ENABLING NATURAL COMPUTING
Xuedong Huang, Microsoft Corporation,
KEYNOTE-2: SPEECH RESEARCH IN TELECOMMUNICATIONS: A
BELL-CENTRIC VIEW
Biing-Hwang (Fblack) Juang, Georgia Institute
of
KEYNOTE-3: SPOKEN LANGUAGE PROCESSING: PEOPLE VERSUS
MACHINES
William Shi-Yuan Wang, The
TUTORIAL-1: MINIMUM CLASSIFICATION ERROR RATE PATTERN
RECOGNITION APPROACH FOR SPEECH AND LANGUAGE PROCESSING
Wu Chou, Avaya Labs Research, Avaya Inc., USA
TUTORIAL-2: MAXIMUM ENTROPY MODELING FOR SPEECH
RECOGNITION
Hong-Kwang Jeff Kuo,
L1: SPEECH RECOGNITION (I)
L1.1: PROGRESS ON MANDARIN CONVERSATIONAL TELEPHONE SPEECH
RECOGNITION
MeiYuh Hwang, Xin Lei, Tim Ng, Ivan Bulyko,
Mari Ostendorf, University of Washington, USA; Andreas Stolcke, Wen Wang, Jing
Zheng, Venkata Ramana Rao Gadde, Martin Graciarena, SRI International, USA; Yan
Huang, International Computer Science Institute, USA; Manhung Siu, The Hong
Kong University of Science and Technology, Hong Kong
L1.2: LARGE VOCABULARY CONTINUOUS MANDARIN SPEECH
RECOGNITION USING FINITE STATE MACHINE
YiCheng Pan, ChiaHsing Yu, LinShan Lee,
National Taiwan University, Taipei
L1.3: A COMPARATIVE STUDY ON VARIOUS CONFIDENCE MEASURES
IN LARGE VOCABULARY SPEECH RECOGNITION
Gang Guo, University of Science and
Technology of China, Hefei; Chao Huang, Microsoft Research Asia,Beijing; Hui
Jiang, York University, Canada; RenHua Wang, University of Science and Technology
of China, Hefei
L1.4: GENERALIZED POSTERIOR PROBABILITY FOR MINIMIZING
VERIFICATION ERRORS AT SUBWORD, WORD AND SENTENCE LEVELS
Wai Kit Lo, Frank K. Soong, Satoshi Nakamura,
ATR, Japan
L1.5: CHINESE LARGE-VOCABULARY NAME RECOGNITION SYSTEM
USING CHARACTER DESCRIPTION AND SYLLABLE SPELLING RECOGNITION
Nick JuiChang Wang, ChingHo Tsai, Patrick
Huang, JiaLin Shen, Delta Electronics Inc., Taipei
L1.6: ERROR IDENTIFICATION FOR LARGE VOCABULARY SPEECH
RECOGNITION
Zhengyu Zhou, Helen Meng, The Chinese
University of Hong Kong, Hong Kong
L2: TOPICS IN SPEECH SCIENCE
L2.1: INVESTIGATION AND MODELING OF COARTICULATION IN
SPEECH PRODUCTION
Jianwu Dang, Jianguo Wei, Takeharu Suzuki,
Japan Advanced Institute of Science and Technology, Ishikawa; Kiyoshi Honda,
ATR Human Information Science Lab, Japan; Pascal Perrier, University Stendhal,
France; Masaaki Honda, Waseda University, Japan
L2.2: SPONTANEOUS MANDARIN PRODUCTION: RESULTS OF A
CORPUS-BASED STUDY
ShuChuan Tseng, Academia Sinica,
L2.3: EFFECTS OF PHONEMIC VS ALLOPHONIC DENSITY AND STRESS
ON VOWEL-TO-VOWEL COARTICULATION IN CANTONESE AND BEIJING MANDARIN
Pik Ki Peggy Mok, Sarah Hawkins,
L2.4: GLOTTALIZATION IN INVENTORY CONSTRUCTION: A
CROSS-LANGUAGE STUDY
Hongwei Ding, Oliver Jokisch, Ruediger
Hoffmann, Dresden University of Technology, Germany
L2.5: FOCUS AND INTONATIONAL PHRASE BOUNDARY IN STANDARD
CHINESE
Yiya Chen,
L2.6: PERCEPTION OF MANDARIN INTONATION
Jiahong Yuan,
L3: SPEAKER AND LANGUAGE RECOGNITION
L3.1: LANGUAGE IDENTIFICATION THROUGH LARGE VOCABULARY
CONTINUOUS SPEECH RECOGNITION
Boon Pang Lim, Haizhou Li, Yu Chen, Institute
for
L3.2: LANGUAGE IDENTIFICATION USING DISCRIMINATIVE
WEIGHTED LANGUAGE MODELS
Shizhen Wang, Jia Liu, Runsheng Liu,
L3.3: TEXT-INDEPENDENT SPEAKER VERIFICATION BASED ON
RELATION OF MFCC COMPONENTS
Guiwen Ou, Dengfeng Ke, Zhongshan University,
Guangzhou
L3.4: ADAPTIVE CONDITIONAL PRONUNCIATION MODELING USING
ARTICULATORY FEATURES FOR SPEAKER VERIFICATION
KaYee Leung, ManWai Mak, The Hong Kong
Polytechnic University, Hong Kong; Manhung Siu, The Hong Kong University of
Science and Technology, Hong Kong; SunYuan Kung, Princeton University, USA
L3.5: UNSEEN HANDSET MISMATCH COMPENSATION BASED ON
FEATURE/MODEL-SPEECH A PRIORI KNOWLEDGE INTERPOLATION FOR ROBUST SPEAKER
RECOGNITION
JyhHer Yang, YuanFu Liao,
L3.6: ROBUST SPEAKER RECOGNITION INTEGRATING PITCH AND
WIENER FILTER
Junmei Bai, Rong Zheng, Bo Xu, Shuwu Zhang,
Chinese Academy of Sciences, Beijing
L4: SPEECH ANALYSIS
L4.1: MODELING GLOTTAL EFFECT ON THE SPECTRAL ENVELOP OF
STRAIGHT USING MIXTURE OF GAUSSIANS
Zhenhua Ling, Yuping Wang, Yu Hu, RenHua
Wang,
L4.2: A NOVEL TWO-STEP SVM CLASSIFIER FOR
VOICED/UNVOICED/SILENCE CLASSIFICATION OF SPEECH
Fengyan Qi, Changchun Bao, Yan Liu, Beijing
University of Technology, Beijing
L4.3: ANALYSIS OF SHANGHAINESE F0 CONTOURS BASED ON THE
COMMAND-RESPONSE MODEL
Wentao Gu, Keikichi Hirose, Hiroya Fujisaki,
The
L4.4: AUTOMATIC DETECTION OF CHINESE ACCENT-INDEX BASED ON
APPROXIMATION-RATIO
Weibin Zhu, Wei Zhang, Qin Shi, Xijun Ma,
Liqin Shen, IBM China Research Lab, Beijing
L4.5: ON ANALYSIS OF EIGENPITCH IN MANDARIN CHINESE
Jilei Tian, Jani Nurminen,
L4.6: ACOUSTICAL STUDY ON SUB-HARMONIC OF GLOTTAL SOURCE
IN MANDARIN TONES
Jiangping Kong,
L5: SPEECH RECOGNITION (II)
L5.1: A STUDY OF SWITCHING STATE SEGMENTATION IN SEGMENTAL
SWITCHING LINEAR GAUSSIAN HIDDEN MARKOV MODELS FOR ROBUST SPEECH RECOGNITION
Donglai Zhu, Qiang Huo, Jian Wu, The
University of Hong Kong, Hong Kong
L5.2: ROBUST FEATURES FOR SPEECH RECOGNITION USING MINIMUM
VARIANCE DISTORTIONLESS RESPONSE (MVDR) SPECTRUM ESTIMATION AND FEATURE
NORMALIZATION TECHNIQUES
Yi Chen, LinShan Lee,
L5.3: DATA-DRIVEN TEMPORAL FILTERS BASED ON MAXIMUM MUTUAL
INFORMATION FOR ROBUST FEATURES IN SPEECH RECOGNITION
YungSheng Huang, Jeihweih Hung,
L5.4: A NEW EIGENVOICE APPROACH TO SPEAKER ADAPTATION
ChihHsien Huang, JenTzung Chien, National
Cheng Kung University, Tainan; Hsinmin Wang, Academia Sinica, Taipei
L5.5: MCE-BASED TRAINING OF SUBSPACE DISTRIBUTION
CLUSTERING HMM
XiaoBing Li, LiRong Dai, RenHua Wang,
University of Science and Technology of China, Hefei
L5.6: A FRAMEWORK FOR FAST SEGMENT MODEL BY AVOIDANCE OF
blackUNDANT COMPUTATION ON SEGMENT
Yun Tang, Wenju Liu, Yiyan Zhang, Bo Xu,
Chinese Academy of Sciences, Beijing
P1: TOPICS IN SPOKEN LANGUAGE PROCESSING
P1.1: DEPENDENCE OF CORRECT PRONUNCIATION OF CHINESE
ASPIRATED SOUNDS ON POWER DURING VOICE ONSET TIME
Akemi Hoshino,
P1.2: EFFECT OF JAPANESE ARTICULATION OF STOPS ON
PRONUNCIATION OF CHINESE ASPIRATED SOUNDS BY JAPANESE STUDENTS
Akemi Hoshino, Toyama National College of
Maritime Technology, Japan; Akio Yassuda, Tokyo University of Marine Science
and Technology, Japan
P1.3: TAIWAN MANDARIN -- DOES IT REMAIN HOMOGENEOUS?
Huiju Hsu,
P1.4: CONTRIBUTIONS OF PERIODICITY FLUCTUATION CUES IN
INDIVIDUAL FREQUENCY CHANNELS TO CHINESE SPEECH RECOGNITION
Xin Luo, University of Science and Technology
of China, Hefei; QianJie Fu, House Ear Institute, USA
P1.5: AUTOMATIC ASSESSMENT OF PRONUNCIATION QUALITY
Bin Dong, Qingwei Zhao, Jianping Zhang,
Yonghong Yan, Chinese Academy of Sciences, Beijing
P1.6: QUANTIZATION OF SEW AND REW MAGNITUDE FOR 2 KB/S
WAVEFORM INTERPOLATION SPEECH CODING
Jing Li, Changchun Bao, Beijing University of
Technology, Beijing
P1.7: LOW COMPLEXITY DECOMPOSITION FOR THE CHARACTERISTIC
WAVEFORM OF SPEECH SIGNAL
Guiping Wang, Changchun Bao, Beijing
University of Technology, Beijing
P1.8: HIGH QUALITY HARMONIC EXCITATION LINEAR PblackICTIVE
SPEECH CODING AT 2 KB/S
Changchun Bao, Beijing University of
Technology, Beijing; Jason Lukasiak, Christian Ritz, University of Wollongong,
Australia
P1.9: AN IMPROVED 4 KBIT/S CELP SPEECH CODING ALGORITHM
Yanning Bai, Changchun Bao, Beijing
University of Technology, Beijing
P1.10: AN EMBEDDED ENGLISH SYNTHESIS APPROACH BASED ON
SPEECH CONCATENATION AND SMOOTHING
P1.11: HEARER MODEL BASED STRESS PblackICTION FOR CHINESE
TTS SYSTEM
GuoPing Hu, QingFeng Liu, Yu Hu, RenHua Wang,
University of Science and Technology of China, Hefei
P1.12: GRAPHEME-TO-PHONEME CONVERSION IN CHINESE TTS
SYSTEM
Honghui Dong, Jianhua Tao, Bo Xu, Chinese
Academy of Sciences, Beijing
P1.13: A MANDARIN TTS SYSTEM WITH AN INTEGRATED PROSODIC
MODEL
ShaoHuang Pin, Yongcheng Chen, Hsinmin Wang,
Chiuyu Tseng, Academia Sinica, Taipei
P1.14: PblackICTING PROSODIC WORDS FROM LEXICAL WORDS--A
FIRST STEP TOWARDS PblackICTING PROSODY FROM TEXT
HuaJui Peng, Chiching Chen, Chiuyu Tseng,
Kehjiann Chen, Academia Sinica,
P1.15: A SUPERPOSED PROSODIC MODEL FOR CHINESE
TEXT-TO-SPEECH SYNTHESIS
GaoPeng Chen, University of Science and
Technology of China, Hefei; Garard Bailly, Institut de la Communication Parle;
QingFeng Liu, RenHua Wang, University of Science and Technology of China, Hefei
P1.16: IMPROVING THE PERFORMANCE OF MGM-BASED VOICE
CONVERSION BY PREPARING TRAINNING DATA METHOD
Guoyu Zuo, Wenju Liu, Chinese Academy of Sciences,
Beijing; Xiaogang Ruan, Beijing University of Technology, Beijing
P1.17: ANALYSIS AND SYNTHESIS OF CANTONESE F0 CONTOURS
BASED ON THE COMMAND-RESPONSE MODEL
Wentao Gu, Keikichi Hirose, Hiroya Fujisaki,
The
P1.18: THE DISAMBIGUATION STRATEGIES OF SEMANTIC ANALYSIS
IN CHINESE SPOKEN DIALOGUE SYSTEM
Bei Liu, Limin Du,
P1.19: BILINGUAL RESPONSE GENERATION USING
SEMI-AUTOMATICALLY-INDUCED TEMPLATES FOR A MIXED-INITIATIVE DIALOG SYSTEM
Wing Lin Yip, Helen Meng, The Chinese
University of Hong Kong, Hong Kong
P1.20: DEVELOPMENT OF A CHINESE TELEPHONY CONVERSATIONAL
CORPUS FOR SPEECH PROCESSING
Yi Liu, Pascale Fung, The Hong Kong
University of Science and Technology, Hong Kong; Shudong Huang, Chris Cieri,
University of Pennsylvania, USA; Lufeng Zhai, Benfeng Chen, The Hong Kong
University of Science and Technology, Hong Kong
L6: SPEECH SYNTHESIS
L6.1: VARIABLE-LENGTH UNIT SELECTION USING LSA-BASED
SYNTACTIC STRUCTURE COST
ChungHsien Wu, ChiChun Hsia, JiunFu Chen,
TeHsien Liu, National Cheng Kung University, Tainan
L6.2: AN ACOUSTIC AND ARTICULATORY KNOWLEDGE INTEGRATED
METHOD FOR IMPROVING SYNTHETIC MANDARIN SPEECH'S FLUENCY
HungYan Gu, KuoHsian Wang,
L6.3: PROSODY AND STYLE CONTROLS IN CU VOCAL USING SSML
AND SAPI XML TAGS
Tien Ying Fung, Yuk Chi Li, Helen Meng, P.C.
Ching, The Chinese University of Hong Kong, Hong Kong
L6.4: APPLY LENGTH DISTRIBUTION MODEL TO INTONATIONAL
PHRASE PblackICTION
JianFeng Li, GuoPing Hu, Ming Fan, LiRong
Dai,
L6.5: INTENSITY IN RELATION TO PROSODY ORGANIZATION
Chiuyu Tseng, Yehlin Lee, Academia Sinica,
L6.6: RHYTHM CORRELATION OF SPEECH SYNTHESIS SYSTEM
Jianhua Tao, Chinese
P2: RECOGNITION OF SPEECH, SPEAKER AND LANGUAGE
P2.1: TRIGRAM DURATION MODELING IN SPEECH RECOGNITION
Yun Tang, Wenju Liu, Bo Xu, Chinese Academy
of Sciences, Beijing
P2.2: A SYSTEM FOR MANDARIN SHORT PHRASE RECOGNITION ON
PORTABLE DEVICES
Chao Xu, Yi Liu, Yongsheng Yang, Pascale
Fung, The Hong Kong University of Science and Technology, Hong Kong; Zhigang
Cao, Tsinghua University, Beijing
P2.3: TONE RECOGNITION FOR CHINESE SPEECH: A COMPARATIVE
STUDY OF MANDARIN AND CANTONESE
Gang Peng, Hongying Zheng, William S.Y. Wang,
City University of Hong Kong, Hong Kong
P2.4: CHINESE-ENGLISH MIXED-LINGUAL KEYWORD SPOTTING
ShanRuei You, ShihChieh Chien, ChihHsing Hsu,
KeShiu Chen, JiaJang Tu, Jeng Shien Lin, SenChia Chang, Industrial Technology
Research Institute, Hsinchu
P2.5: AN ACOUSTIC-PHONETIC ANALYSIS OF LARGE VOCABULARY
CONTINUOUS MANDARIN SPEECH RECOGNITION FOR NON-NATIVE SPEAKERS
Jian Yang, Yuanyuan Pu, Hong Wei,
P2.6: FEATURE MASKING IN AN EMBEDDED MANDARIN SPEECH
RECOGNITION SYSTEM
Yuezhong Tang, Xia Wang, Yang Cao, Feng Ding,
Nokia Research Center, Beijing
P2.7: ENERGY CONTOUR ENHANCEMENT FOR NOISY SPEECH
RECOGNITION
TaiHwei Hwang, SenChia Chang, Industrial
Technology Research Institute, Hsinchu
P2.8: DOUBLE GAUSSIAN BASED FEATURE NORMALIZATION FOR
ROBUST SPEECH RECOGNITION
Bo Liu, LiRong Dai, JinYu Li, RenHua Wang,
University of Science and Technology of China, Hefei
P2.9: A STUDY ON MANDARIN BROADCAST NEWS SPEECH
RECOGNITION
C.L. Chen, Y.R. Wang, S.H. Chen,
P2.10: TASK-SPECIFIC ADAPTATION IN CHINESE NAME
RECOGNITION
GuoHong Ding, Nokia Research Center, Beijing;
Bo Xu, Chinese Academy of Sciences, Beijing; Xia Wang, Yang Cao, Feng Ding,
Yuezhong Tang, Nokia Research Center, Beijing
P2.11: INTEGRATING TONAL INFORMATION INTO MANDARIN NAME
RECOGNITION WITH DIFFERENT STRATEGIES
Dongsheng Luo, Xiang Xie, Jingming Kuang,
Beijing Institute of Technology,
P2.12: DISCRIMINATIVE TRANSFORM FOR CONFIDENCE ESTIMATION
IN MANDARIN SPEECH RECOGNITION
Gang Guo, RenHua Wang,
P2.13: AN INVESTIGATION INTO SUBSPACE RAPID SPEAKER
ADAPTAION
Michael Zhang, Jun Xu,
P2.14: ON NOISE ROBUSTNESS OF DYNAMIC AND STATIC FEATURES
FOR CONTINUOUS CANTONESE DIGIT RECOGNITION
Chen Yang, The Chinese University of Hong
Kong, Hong Kong; Frank K. Soong, ATR, Japan; Tan Lee, The Chinese University of
Hong Kong, Hong Kong
P2.15: A TWO-STEP KEYWORD SPOTTING METHOD BASED ON
CONTEXT-DEPENDENT A POSTERIORI PROBABILITY
Thomas Fang Zheng, Jing Li, Tsinghua
University, Beijing; Zhanjiang Song, Beijing d-Ear Technologies Co.Ltd,
Beijing; Mingxing Xu, Tsinghua University, Beijing
P2.16: A METHOD OF ESTIMATING THE EQUAL ERROR RATE FOR
AUTOMATIC SPEAKER VERIFICATION
JyhMin Cheng, HsiaoChuan Wang, National Tsing
Hua University, Hsinchu
P2.17: TEXT-INDEPENDENT SPEAKER IDENTIFICATION USING
GMM-UBM AND FRAME LEVEL LIKELIHOOD NORMALIZATION
Rong Zheng, Shuwu Zhang, Bo Xu, Chinese
Academy of Sciences, Beijing
P2.18: DETECTION OF LANGUAGE BOUNDARY IN CODE-SWITCHING
UTTERANCES BY BI-PHONE PROBABILITIES
Joyce Y.C. Chan, P.C. Ching, Tan Lee, Helen
Meng, The Chinese University of Hong Kong, Hong Kong
P2.19: CANTONESE VERBAL INFORMATION VERIFICATION SYSTEM
USING GMM-BASED ANTI-MODEL
Chao Qin, Tan Lee, The Chinese
P2.20: EMOTION RECOGNITION FROM MADARIN SPEECH SIGNALS
TsangLong Pao, YuTe Chen, JunHeng Yeh,
L7: LANGUAGE MODELING AND SPOKEN LANGUAGE TRANSLATION
L7.1: EXPLOITING SYNTACTIC, SEMANTIC AND LEXICAL
REGULARITIES IN LANGUAGE MODELING VIA DIRECTED MARKOV RANDOM FIELDS
Shaojun Wang, University of Alberta, Canada;
Shaomin Wang, Massachusetts Institute of Technology, USA; Russell Greiner, Dale
Schuurmans, Li Cheng, University of Alberta, Canada
L7.2: A MAXIMUM ENTROPY APPROACH FOR INTEGRATING SEMANTIC
INFORMATION IN STATISTICAL LANGUAGE MODELS
ChuangHua Chueh, JenTzung Chien, National
Cheng Kung University, Tainan; Hsinmin Wang, Academia Sinica, Taipei
L7.3: STATISTICAL LANGUAGE MODEL ADAPTATION FOR MANDARIN
BROADCAST NEWS TRANSCRIPTION
Berlin Chen, WenHung Tsai, JenWei Kuo,
National Taiwan Normal University, Taipei
L7.4: USE OF DIRECT MODELING IN NATURAL LANGUAGE
GENERATION FOR CHINESE AND ENGLISH TRANSLATION
FuHua Liu, Yuqing Gao, IBM T.J. Watson
Research Center, USA
L7.5: A NEW TWO-LAYER APPROACH FOR SPOKEN LANGUAGE
TRANSLATION
JhingFa Wang, ShunChieh Lin, HsuehWei Yang,
L7.6: ANALYSIS OF PARAPHRASED CORPUS AND LEXICL-BASED
APPROACH TO CHINESE PARAPHRASING
Yan Zhang, Hideki Kashioka, ATR,
L8: APPLICATIONS OF SPOKEN LANGUAGE PROCESSING TECHNOLOGY
L8.1: AN INITIAL PROTOTYPE SYSTEM FOR CHINESE SPOKEN
DOCUMENT UNDERSTANDING AND ORGANIZATION FOR INDEXING/BROWSING AND RETRIEVAL
APPLICATIONS
LinShan Lee, ShunChuan Chen, Yuan Ho, JiaFu
Chen, MingHan Li, Tehsuan Li, National Taiwan University, Taipei
L8.2: SPOKEN DOCUMENT SUMMARIZATION USING TOPIC-RELATED
CORPUS AND SEMANTIC DEPENDENCY GRAMMAR
ChiaHsin Hsieh, ChienLin Huang, ChungHsien
Wu,
L8.3: COMPUTER ASSISTED SPOKEN ENGLISH LEARNING FOR
CHINESE IN TAIWAN
JiangChun Chen, JuiLin Lo, JyhShing Roger
Jang,
L8.4: SECOND LANGUAGE ACQUISITION THROUGH HUMAN COMPUTER
DIALOGUE
Stephanie Seneff, Chao Wang, Mitchell
Peabody, Victor Zue, Massachusetts Institute of
L8.5: AN INFORMATION GAIN AND GRAMMAR COMPLEXITY BASED APPROACH
TO ATTRIBUTE SELECTION IN SPEECH ENABLED INFORMATION RETRIEVAL DIALOGS
Haiping Li, Haixin Chai, IBM China Research
Lab, Beijing