Chinese Spoken Language Processing: 5th International Symposium, ISCSLP 2006, Singapore, December 13-16, 2006. Proceedings

Front Matter....Pages -
Interactive Computer Aids for Acquiring Proficiency in Mandarin....Pages 1-12
The Affective and Pragmatic Coding of Prosody....Pages 13-14
Challenges in Machine Translation....Pages 15-15
Automatic Indexing and Retrieval of Large Broadcast News Video Collections – The TRECVID Experience....Pages 16-16
An HMM-Based Approach to Flexible Speech Synthesis....Pages 17-17
Text Information Extraction and Retrieval....Pages 18-18
Mechanisms of Question Intonation in Mandarin....Pages 19-30
Comparison of Perceived Prosodic Boundaries and Global Characteristics of Voice Fundamental Frequency Contours in Mandarin Speech....Pages 31-42
Linguistic Markings of Units in Spontaneous Mandarin....Pages 43-54
Phonetic and Phonological Analysis of Focal Accents of Disyllabic Words in Standard Chinese....Pages 55-66
Focus, Lexical Stress and Boundary Tone: Interaction of Three Prosodic Features....Pages 67-75
A Robust Voice Activity Detection Based on Noise Eigenspace Projection....Pages 76-86
Pitch Mean Based Frequency Warping....Pages 87-94
A Study of Knowledge-Based Features for Obstruent Detection and Classification in Continuous Mandarin Speech....Pages 95-105
Speaker-and-Environment Change Detection in Broadcast News Using Maximum Divergence Common Component GMM....Pages 106-115
UBM Based Speaker Segmentation and Clustering for 2-Speaker Detection....Pages 116-125
Design of Cubic Spline Wavelet for Open Set Speaker Classification in Marathi....Pages 126-137
Rhythmic Organization of Mandarin Utterances — A Two-Stage Process....Pages 138-148
Prosodic Boundary Prediction Based on Maximum Entropy Model with Error-Driven Modification....Pages 149-160
Prosodic Words Prediction from Lexicon Words with CRF and TBL Joint Method....Pages 161-168
Prosodic Word Prediction Using a Maximum Entropy Approach....Pages 169-178
Predicting Prosody from Text....Pages 179-188
Nonlinear Emotional Prosody Generation and Annotation....Pages 189-199
A Unified Framework for Text Analysis in Chinese TTS....Pages 200-210
Speech Synthesis Based on a Physiological Articulatory Model....Pages 211-222
An HMM-Based Mandarin Chinese Text-To-Speech System....Pages 223-232
HMM-Based Emotional Speech Synthesis Using Average Emotion Model....Pages 233-240
A Hakka Text-To-Speech System....Pages 241-247
Adaptive Null-Forming Algorithm with Auditory Sub-bands....Pages 248-257
Multi-channel Noise Reduction in Noisy Environments....Pages 258-269
Minimum Phone Error (MPE) Model and Feature Training on Mandarin Broadcast News Task....Pages 270-281
State-Dependent Phoneme-Based Model Merging for Dialectal Chinese Speech Recognition....Pages 282-293
Non-uniform Kernel Allocation Based Parsimonious HMM....Pages 294-302
Consistent Modeling of the Static and Time-Derivative Cepstrums for Speech Recognition Using HSPTM....Pages 303-314
Vector Autoregressive Model for Missing Feature Reconstruction....Pages 315-324
Auditory Contrast Spectrum for Robust Speech Recognition....Pages 325-334
Signal Trajectory Based Noise Compensation for Robust Speech Recognition....Pages 335-345
An HMM Compensation Approach Using Unscented Transformation for Noisy Speech Recognition....Pages 346-357
Noisy Speech Recognition Performance of Discriminative HMMs....Pages 358-369
Distributed Speech Recognition of Mandarin Digits String....Pages 370-379
Unsupervised Speaker Adaptation Using Reference Speaker Weighting....Pages 380-389
Automatic Construction of Regression Class Tree for MLLR Via Model-Based Hierarchical Clustering....Pages 390-398
A Minimum Boundary Error Framework for Automatic Phonetic Segmentation....Pages 399-409
Advances in Mandarin Broadcast Speech Transcription at IBM Under the DARPA GALE Program....Pages 410-421
Improved Large Vocabulary Continuous Chinese Speech Recognition by Character-Based Consensus Networks....Pages 422-434
All-Path Decoding Algorithm for Segmental Based Speech Recognition....Pages 435-444
Improved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone Models....Pages 445-453
On Using Entropy Information to Improve Posterior Probability-Based Confidence Measures....Pages 454-463
Vietnamese Automatic Speech Recognition: The FLaVoR Approach....Pages 464-474
Language Identification by Using Syllable-Based Duration Classification on Code-Switching Speech....Pages 475-484
CCC Speaker Recognition Evaluation 2006: Overview, Methods, Data, Results and Perspective....Pages 485-493
The IIR Submission to CSLP 2006 Speaker Recognition Evaluation....Pages 494-505
A Novel Alternative Hypothesis Characterization Using Kernel Classifiers for LLR-Based Speaker Verification....Pages 506-517
Speaker Verification Using Complementary Information from Vocal Source and Vocal Tract....Pages 518-528
ISCSLP SR Evaluation, UVA–CS_es System Description. A System Based on ANNs....Pages 529-538
Evaluation of EMD-Based Speaker Recognition Using ISCSLP2006 Chinese Speaker Recognition Evaluation Corpus....Pages 539-548
Integrating Complementary Features with a Confidence Measure for Speaker Identification....Pages 549-557
Discriminative Transformation for Sufficient Adaptation in Text-Independent Speaker Verification....Pages 558-565
Fusion of Acoustic and Tokenization Features for Speaker Recognition....Pages 566-577
Contextual Maximum Entropy Model for Edit Disfluency Detection of Spontaneous Speech....Pages 578-589
Automatic Detection of Tone Mispronunciation in Mandarin....Pages 590-601
Towards Automatic Tone Correction in Non-native Mandarin....Pages 602-613
A Corpus-Based Approach for Cooperative Response Generation in a Dialog System....Pages 614-626
A Cantonese Speech-Driven Talking Face Using Translingual Audio-to-Visual Conversion....Pages 627-639
The Implementation of Service Enabling with Spoken Language of a Multi-modal System Ozone....Pages 640-647
Spoken Correction for Chinese Text Entry....Pages 648-659
Extractive Chinese Spoken Document Summarization Using Probabilistic Ranking Models....Pages 660-671
Meeting Segmentation Using Two-Layer Cascaded Subband Filters....Pages 672-682
A Multi-layered Summarization System for Multi-media Archives by Understanding and Structuring of Chinese Spoken Documents....Pages 683-692
Initial Experiments on Automatic Story Segmentation in Chinese Spoken Documents Using Lexical Cohesion of Extracted Named Entities....Pages 693-703
Some Improvements in Phrase-Based Statistical Machine Translation....Pages 704-711
Automatic Spoken Language Translation Template Acquisition Based on Boosting Structure Extraction and Alignment....Pages 712-723
HKUST/MTS: A Very Large Scale Mandarin Telephone Speech Corpus....Pages 724-735
The Paradigm for Creating Multi-lingual Text-To-Speech Voice Databases....Pages 736-747
Multilingual Speech Corpora for TTS System Development....Pages 748-759
Construct Trilingual Parallel Corpus on Demand....Pages 760-767
The Contribution of Lexical Resources to Natural Language Processing of CJK Languages....Pages 768-780
Multilingual Spoken Language Corpus Development for Communication Research....Pages 781-791
Development of Multi-lingual Spoken Corpora of Indian Languages....Pages 792-801
Back Matter....Pages -