Session Index - ISCSLP 2000

Or01          Acoustic Phonetics And Speech Analysis

Context-Independent Chinese Initial-Final Acoustic Modeling Or01.002
Frequency Analysis of the Vowels in Cantonese Or01.068
Annotation and Use of Speech Production Corpus for Building Language-Universal Speech Recognizers Or01.093
Rule-Based Word Pronunciation Networks Generation for Mandarin Speech Recognition Or01.104
Prosodic Structure and Hierarchical Stress in Utterace of Standard Chinese --- One of Cues to Chinese Intonation Or01.114
Speech Corpus Collection and Annotation Or01.116

Or02         Recognition and Understanding of Spoken Language

A New Framework for Mandarin LVCSR Based on One-Pass Decoder Or02.049
The Design of Dialogue Management in a Mixed Initiative Chinese Spoken Dialogue System Engine Or02.054
Computer-Aided Design/Analysis for Chinese Spoken Dialogue Systems Or02.079
Simulating Real Speech Recognizers for the Performance Evaluation of Spoken Language Systems Or02.086
Error-Tolerant and Goal-Oriented Approach in Designing a Mandarin Spoken Dialogue System Or02.096
Comprehension Across Application Domains and Languages Or02.103

Or03         Generation and Synthesis of Spoken Language

Hand Gesture Recognition Based on Decision Tree Or03.027
An Example-Based Approach for Prosody Generation in Chinese Speech Synthesis Or03.032
Strategy and Tactics on the Enhancement of Naturalness in Chinese TTS Or03.039
An Efficient Method to Synthesize Chinese Speech with Speaker Style Or03.043
Experimental Evaluation of a Functional Modeling of Fundamental Frequency Contours of Standard Chinese Sentences Or03.063
Impact of Tone Information on Chinese Name Recognition Or03.115

Or04         Robust Speech Recognition and Language Modeling

A Self Adapting Endpoint Detection Algorithm for Speech Recognition in Noisy Environment Based on 1/f Process Or04.004
Online Unsupervised Learning of HMM Parameters for Speaker Adaptation Or04.040
Word Error Rate Reduction by Bottom-Up Tone Integration to Chinese Continuous Speech Recognition System Or04.052
Optimization of N-Gram Parameters for Natural Language Processing Or04.092
A Multi-Path Syllable to Word Decoder with Language Model Optimization and Automatic Lexicon Augmentation Or04.108
N-Gram Language Model Compression Using Scalar Quantization and Incremental Coding Or04.111

Or05         Information Access by Speech and Speech Translation

Automatic Segmentation and Labeling of Speech Corpus Based on HMM with Adaptation Or05.042
Model Distance and Its Application on Mixed-language Speech Recognition System Or05.045
Benchmark Results of Triphone-Based Acoustic Modeling on HKU96 and HKU99 Putonghua Corpora Or05.056
Global Information Access by Chinese Spoken Language in A Wireless Era -- Overview With Some Recent Results Or05.082
Design and Implementation of A Chinese-to-English Spoken Language Translation System Or05.109

PsA1         Speech analysis and Speech Synthesis

Intra-Syllable Dependent Phonetic Modeling for Chinese Speech Recognition PsA1.005
Modeling of Three Types of Auditory Nerve and its Application in Speech Recognition PsA1.034
A Hierarchic Processing Model In Chinese TTS PsA1.044
A Promising Sysllable Decomposition Method for Tone Languages' Speech Recognition PsA1.046
Modeling and Decision Tree Based Prediction of Pitch Contour in IBM Mandarin Speech Synthesis System PsA1.048
Some Prosodic Properties of MAT Speech Database PsA1.058
Sub-Syllabic Acoustic Modeling Across Chinese DialectsPsA1.062
Prosodic Alternative Units in A Mandarin Chinese Speech Synthesizer PsA1.065
A CART-Based Hierarchical Stochastic Model for Prosodic Phrasing in Chinese PsA1.069
A Min-Nan Text-to-Speech System PsA1.072
A Subband Speech Coding Scheme Based On Code Excited Linear Predictive Coding PsA1.080
The Features of Chinese Computer-Aided Language Learning System PsA1.081
A Study of Phoneme and Syllable Duration Characteristics of Mandarin Chinese PsA1.084
A Sentence-Pitch-Contour Generation Method Using VQ/HMM for Mandarin Text-to-Speech PsA1.094
A Study on The Contribution of Lexical Tones in Chinese LVCSR PsA1.098
Corpus-Based Cantonese Speech Synthesis with Non-Uniform Units PsA1.100
Linguistic Features Selection in Fundament Frequency Patterns PsA1.105

PsA2         Acoustic Modeling

Acoustic Level Error Analysis in Continuous Speech Recognition PsA2.003
Tone Recogniton of Chinese Continuous Speech PsA2.008
A Noise Cancellation Method Based on Wavelet Transform PsA2.010
Primary Research on the Viseme System in Standard Chinese PsA2.036
Speech Interactive Web Page Designing and Implantation Based on Agent PsA2.038
Keyword Spotting in Auto-Attendant System PsA2.053
Duration Modeling in Mandarin Connected Digit Recognition PsA2.059
A Divergence-Based Model Separation PsA2.061
An Adaptive Information Retrieval System Based on Fuzzy Set PsA2.076
A Time-Domain Female-Male Voice Conversion Algorithm PsA2.078
CCL eAttendant - An On-line Auto Attendant System PsA2.097

PsB1         Recognition and Understanding of Spoken Language

Word-Class Stochastic Model in A Spoken Language Dialogue System PsB1.001
EasyCmd: Navigation by Voice Commands PsB1.006
Experiments and Analysis for Speaker Dependent Mandarin Syllable Recognition PsB1.009
A Comparison Between Synthetic Speech And Natural Speech of Chinese PsB1.023
A Robust Method Based on Likelihood Estimation for Speech Signal Detecion PsB1.028
An New Approach for Incremental Speaker Adaptation PsB1.041
Develop Telephony Speech Recognition Systems for Real-world Application PsB1.050
Noise-Robust Speech Recognition Based on Reliable Bands PsB1.060
A Multilingual Spoken Dialog System PsB1.064
Selection of Different Language Model using Dialogue State PsB1.067
The Analysis of Copus Oriented Spoken Chinese Dialog Understanding PsB1.071
On Integrating Tonal Information Into Chinese Speech Recognition PsB1.073
Keyword Spotting by Searching The Syllable Lattices PsB1.087
RCD Sub-Syllable HMM Modeling by Decision Tree Clustering using MAT-2000 Database PsB1.095
Initial Experiments on Recognition of Internet-Accessible Compressed Mandarin Speech PsB1.099

PsB2         Speaker Verification and Speech Translation

Improved Strategies for Intelligent Sentence Input Method Engine System PsB2.007
An Enhanced RASTA Processing for Speaker Identification PsB2.024
Coarticulation and Application of Lateral in Standard Chinese in Speaker Identification PsB2.029
An Interlingua for Dialogue Translation PsB2.030
On Use of GMM for Multilingual Speaker Verification: An Empirical Study PsB2.037
Comparison of Several Smoothing Methods in Statistical Language Model PsB2.047
Statistical Approach to Chinese-English Spoken-Language Translation in Hotel Reservation Domain PsB2.057
Unsupervised Word Induction Using MDL Criterion PsB2.070
Block Analysis of Bilingual Corpus for Chinese-English Statistical Machine Translation PsB2.077
Semi-Class-Based N-Gram Language Modeling for Chinese Dictation PsB2.085
Lexicon Optimization for Chinese Language Modeling PsB2.101
Rule-Based Post-Processing of Pinyin to Chinese Characters Conversion System PsB2.106
Chinese Pinyin Input Method for Mobile Phone PsB2.113

Keynote Speech

Recent Trends in NLP Research HUANG Changning
From Graphical to Voice User Interface: The Next Revolution LEE Chin-Hui
Topics on Minimum Classification Error Rate Based Discriminant Function Approach to Speech Recognition CHOU Wu
Toward Making Speech Part of People's Daily Life YAN Yonghong
A Corpus-Based Prosodic Modeling Method for Mandarin and Min-Nan Text-to-Speech Conversions CHEN Sin-Horng
Processing Some Special Features in Chinese Speech Recognition XU Bo, HUANG Taiyi