Qiang Huo Bin Ma
Eng-Siong Chng Haizhou Li (Eds.)



Chinese
Spoken Language
Processing

5th International Symposium, ISCSLP 2006
Singapore, December 13-16, 2006
Proceedings




   Springer
                        T able of Contents



P lenary
I nteractive Computer Aids for Acquiring Proficiency in Mandarin     1
     Stephanie Seneff

T he Affective and Pragmatic Coding of Prosody                       13
    Klaus R. Scherer

Challenges in Machine Translation                                    15
  Franz Josef Och

A utomatic Indexing and Retrieval of Large Broadcast News Video
Collections - The TRECVID Experience                                 16
    Tat-Seng Chua


T utorial
An HMM-Based Approach to Flexible Speech Synthesis                   17
   Keiichi Tokuda

Text Information Extraction and Retrieval                            18
   Hang Li

Topics in Speech Science
Mechanisms of Question Intonation in Mandarin                        19
  Jiahong Yuan

Comparison of Perceived Prosodic Boundaries and Global
C haracteristics of Voice Fundamental Frequency Contours
in Mandarin Speech                                                   31
    Wentao Gu, Keikichi Hirose, Hiroya Fujisaki

Linguistic Markings of Units in Spontaneous Mandarin                 43
   Shu-Chuan Tseng

P honetic and Phonological Analysis of Focal Accents of Disyllabic
Words in Standard Chinese                                            55
    Yuan Jia, Ziyu Xiong, Aijun Li
XVIII   Table of Contents

Focus, Lexical Stress and Boundary Tone: Interaction of Three Prosodic
F eatures                                                                 67
    Lu Zhang, Yi-Qing Zu, Run-Qiang Yan

S peech Analysis

A R obust Voice Activity Detection Based on Noise Eigenspace
P rojection                                                               76
    Dongwen Ying, Yu SM, Frank Soong, Jianwu Dang, Xugang Lu

P itch Mean Based Frequency Warping                                       87
     Jian Liu, Thomas Fang Zheng, Wenhu Wu

A S tudy of Knowledge-Based Features for Obstruent Detection
and Classification in Continuous Mandarin Speech                          95
   Kuang-Ting Sung, Hsiao-Chuan Wang

S peaker-and-Environment Change Detection in Broadcast News Using
Maximum Divergence Common Component GMM                                  106
    Yih-Ru Wang

UBM Based Speaker Segmentation and Clustering for 2-Speaker
Detection                                                                116
   Jing Deng, Thomas Fang Zheng, Wenhu Wu

Design of Cubic Spline Wavelet for Open Set Speaker Classification in
M arathi                                                                 126
   Hemant A. Paul, T.K. Basu

S peech Synthesis and Generation

R hythmic Organization of Mandarin Utterances — A Two-Stage
Process                                                                  138
   Min Chu, Yunjia Wang

Prosodic Boundary Prediction Based on Maximum Entropy Model
with Error-Driven Modification                                           149
   Xiaonan Zhang, Jun Xu, Lianhong Cai

Prosodic Words Prediction from Lexicon Words with CRF and TBL
J oint Method                                                            161
    Heng Kang, Wenju Liu
                                                      Table of Contents   XIX

P rosodic Word Prediction Using a Maximum Entropy Approach                169
    Honghui Dong, Jianhua Tao, Bo Xu

P redicting Prosody from Text                                             179
    Keh-Jiann Chen, Chiu-yu Tseng, Chia-hung Tai

Nonlinear Emotional Prosody Generation and Annotation                     189
  Jianhua Tao, Jian Yu, Yongguo Kang

A Unified Framework for Text Analysis in Chinese TTS                      200
   Guohong Fu, Min Zhang, GuoDong Zhou, Kang-Kuong Luke

Speech Synthesis Based on a Physiological Articulatory Model              211
   Qiang Fang, Jianwu Dang

An HMM-Based Mandarin Chinese Text-To-Speech System                       223
   Yao Qian, Frank Soong, Yining Chen, Min Chu

HMM-Based Emotional Speech Synthesis Using Average Emotion
Model                                                                     233
  Long Qin, Zhen-Hua Ling, Yi-Jian Wu, Bu-Fan Zhang,
  Ren-Hua Wang

A Hakka Text-To-Speech System                                             241
  Hsiu-Min Yu, Hsin-Te Hwang, Dong-Yi Lin, Sin-Horng Chen


S peech E n h a n c e m e n t
A daptive Null-Forming Algorithm with Auditory Sub-bands                  248
   Heng Zhang, Qiang Fu, Yonghong Yan

Multi-channel Noise Reduction in Noisy Environments                       258
  Junfeng Li, Masato Akagi, Yöiti Suzuki

A coustic Modeling for A u t o m a t i c Speech Recognition

Minimum Phone Error (MPE) Model and Feature Training
on Mandarin Broadcast News Task                                           270
   Jia-Yu Chen, Chia-Yu Wan, Yi Chen, Berlin Chen, Lin-shan Lee

S tate-Dependent Phoneme-Based Model Merging for Dialectal Chinese
Speech Recognition                                                        282
    Linquan Liu, Thomas Fang Zheng, Wenhu Wu
XX     Table of Contents

Non-uniform Kernel Allocation Based Parsimonious HMM              294
  Peng Liu, Jian-Lai Zhou, Frank Soong

Consistent Modeling of the Static and Time-Derivative Cepstrums
for Speech Recognition Using HSPTM                                303
    Yiu-Pong Lai, Man-Hung Siu


R obust Speech Recognition
Vector Autoregressive Model for Missing Feature Reconstruction    315
   Xiong Xiao, Haizhou Li, Eng-Siong Chng

A uditory Contrast Spectrum for Robust Speech Recognition         325
   Xugang Lu, Jianwu Dang

Signal Trajectory Based Noise Compensation for Robust Speech
Recognition                                                       335
   Zhi-Jie Yan, Jian-Lai Zhou, Frank Soong, Ren-Hua Wang

An HMM Compensation Approach Using Unscented Transformation
for Noisy Speech Recognition                                      346
    Yu Hu, Qiang Huo

Noisy Speech Recognition Performance of Discriminative HMMs       358
   Jun Du, Peng Liu, Frank Soong, Jian-Lai Zhou, Ren-Hua Wang

D istributed Speech Recognition of Mandarin Digits String         370
    Yih-Ru Wang, Bo-Xuan Lu, Yuan-Fu Liao, Sin-Horng Chen


Speech Adaptation/Normalization
Unsupervised Speaker Adaptation Using Reference Speaker
Weighting                                                         380
   Tsz-Chung Lai, Brian Mak

A utomatic Construction of Regression Class Tree for MLLR Via
Model-Based Hierarchical Clustering                               390
   Shih-Sian Cheng, Yeong-Yuh Xu, Hsin-Min Wang, Hsin-Chia Fu

G eneral Topics in Speech Recognition
A Minimum Boundary Error Framework for Automatic Phonetic
Segmentation                                                      399
   Jen-Wei Kuo, Hsin-Min Wang
                                                      Table of Contents   XXI

L arge Vocabulary Continuous Speech Recognition
Advances in Mandarin Broadcast Speech Transcription at IBM Under
t he DARPA GALE Program                                                   410
     Yong Qin, Qin Shi, Yi Y. Liu, Hagai Aronowitz, Stephen M. Chu,
    Hong-Kwang Kuo, Geoffrey Zweig

Improved Large Vocabulary Continuous Chinese Speech Recognition
by Character-Based Consensus Networks                                     422
   Yi-Sheng Fu, Yi-Cheng Pan, Lin-shan Lee

A ll-Path Decoding Algorithm for Segmental Based Speech
Recognition                                                               435
     Yun Tang, Wenju Liu, Bo Xu

Improved Mandarin Speech Recognition by Lattice Rescoring with
E nhanced Tone Models                                                     445
   Huanliang Wang, Yao Qian, Frank Soong, Jian-Lai Zhou, Jiqing Han

On Using Entropy Information to Improve Posterior Probability-Based
Confidence Measures                                                       454
   Tzan-Hwei Chen, Berlin Chen, Hsin-Min Wang

Vietnamese Automatic Speech Recognition: The FLaVoR Approach              464
   Quan Vu, Kris Demuynck, Dirk Van Compernolle


M ultilingual Recognition and Identification
Language Identification by Using Syllable-Based Duration Classification
on Code-Switching Speech                                                  475
   Dau-cheng Lyu, Ren-yuan Lyu, Yuang-chin Chiang, Chun-nan Hsu


S peaker Recognition and Characterization
CCC Speaker Recognition Evaluation 2006: Overview, Methods, Data,
Results and Perspective                                                   485
   Thomas Fang Zheng, Zhanjiang Song, Lihong Zhang,
   Michael Brasser, Wei Wu, Jing Deng

T he HR Submission to CSLP 2006 Speaker Recognition Evaluation            494
    Kong-Aik Lee, Hanwu Sun, Rong Tong, Bin Ma, Minghui Dong,
    Changhuai You, Donglai Zhu, Chin-Wei Eugene Koh, Lei Wang,
    Torai Kinnunen, Eng-Siong Chng, Haizhou Li
XXII   Table of Contents

A Novel Alternative Hypothesis Characterization Using Kernel
Classifiers for LLR-Based Speaker Verification                    506
   Yi-Hsiang Chao, Hsin-Min Wang, Ruei-Chuan Chang

Speaker Verification Using Complementary Information from Vocal
Source and Vocal Tract                                            518
   Nengheng Zheng, Ning Wang, Tan Lee, P. C. Ching

I SCSLP SR Evaluation, UVA-CS.es System Description. A System
Based on ANNs                                                     529
    Carlos E. Vivaracho

E valuation of EMD-Based Speaker Recognition Using ISCSLP2006
Chinese Speaker Recognition Evaluation Corpus                     539
    Shingo Kuroiwa, Satoru Tsuge, Masahiko Kita, Fuji Ren

I ntegrating Complementary Features with a Confidence Measure
for Speaker Identification                                        549
    Nengheng Zheng, P. C. Ching, Ning Wang, Tan Lee

Discriminative Transformation for Sufncient Adaptation
in Text-Independent Speaker Verification                          558
   Hao Yang, Yuan Dong, Xianyu Zhao, Jian Zhao, Haila Wang

Fusion of Acoustic and Tokenization Features for Speaker
Recognition                                                       5§5
   Rong Tong, Bin Ma, Kong-Aik Lee, Changhuai You, Donglai Zhu,
   Tomi Kinnunen, Hanwu Sun, Minghui Dong, Eng-Siong Chng,
   Haizhou Li

S poken Language U n d e r s t a n d i n g

C ontextual Maximum Entropy Model for Edit Disfluency Detection
of Spontaneous Speech                                             578
    Jui-Feng Yeh, Chung-Hsien Wu, Wei-Yen Wu

H u m a n Language Acquisition, Development and
L earning

A utomatic Detection of Tone Mispronunciation in Mandarin         590
   Li Zhang, Chao Huang, Min Chu, Frank Soong, Xianda Zhang,
    Yudong Chen

Towards Automatic Tone Correction in Non-native Mandarin          602
  Mitchell Peabody, Stephanie Seneff
                                                      Table of Contents   XXIII

S poken and M u l t i m o d a l Dialog Systems
A Corpus-Based Approach for Cooperative Response Generation
in a Dialog System                                                          614
    Zhiyong Wu, Helen Meng, Hui Ning, Sam C. Tse

A C antonese Speech-Driven Talking Face Using Translingual
Audio-to-Visual Conversion                                                  627
  Lei Xie, Helen Meng, Zhi-Qiang Liu

T he Implementation of Service Enabling with Spoken Language
of a Multi-modal System Ozone                                               640
    Sen Zhang, Yves Laprie

Spoken Correction for Chinese Text Entry                                    648
   Bo-June Paul Hsu, James Glass

S peech D a t a Mining and D o c u m e n t Retrieval

E xtractive Chinese Spoken Document Summarization Using
P robabilistic Ranking Models                                               660
    Yi-Ting Chen, Suhan Yu, Hsin-Min Wang, Berlin Chen

Meeting Segmentation Using Two-Layer Cascaded Subband Filters               672
  Manuel Giuliani, Tin Lay Nwe, Haizhou Li

A Multi-layered Summarization System for Multi-media Archives
by Understanding and Structuring of Chinese Spoken Documents                683
   Lin-shan Lee, Sheng-yi Kong, Yi-cheng Pan, Yi-sheng Fu,
   Yu-tsun Huang, Chien-chih Wang

Initial Experiments on Automatic Story Segmentation in Chinese
Spoken Documents Using Lexical Cohesion of Extracted Named
E ntities                                                                   693
    Devon Li, Wai-Kit Lo, Helen Meng

M achine Translation of Speech
Some Improvements in Phrase-Based Statistical Machine Translation . . . .   704
   Zhendong Yang, Wei Pang, Jinhua Du, Wei Wei, Bo Xu

A utomatic Spoken Language Translation Template Acquisition Based
on Boosting Structure Extraction and Alignment                              712
   Rile Hu, Xia Wang
XXIV   Table of Contents

Spoken Language Resources and Annotation
H KUST/MTS: A Very Large Scale Mandarin Telephone Speech
C orpus                                                                 724
    Yi Liu, Pascale Fung, Yongsheng Yang, Christopher Cieri,
    Shudong Huang, David Graff

T he Paradigm for Creating Multi-lingual Text-To-Speech Voice
D atabases                                                              736
    Min Chu, Yong Zhao, Yining Chen, Lijuan Wang, Frank Soong

Multilingual Speech Corpora for TTS System Development                  748
  Hsi-Chun Hsiao, Hsiu-Min Yu, Yih-Ru Wang, Sin-Horng Chen

C onstruct Trilingual Parallel Corpus on Demand                         760
   Muyun Yang, Hongfei Jiang, Tiejun Zhao, Sheng Li

T he Contribution of Lexical Resources to Natural Language Processing
of CJK Languages                                                        768
    Jack Halpern

Multilingual Spoken Language Corpus Development for Communication
Research                                                                781
   Toshiyuki Takezawa

Development of Multi-lingual Spoken Corpora of Indian Languages         792
  K. Samudravijaya


A uthor Index                                                           803