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

by Huo, Qiang; Ma, Bin; Chng, Eng-siong; Li, Haizhou

• ISBN13: 9783540496656
• ISBN10: 3540496653
• Format: Paperback
• Copyright: 2007-02-03
• Publisher: Springer Verlag

Summary

This book constitutes the thoroughly refereed proceedings of the 5th International Symposium on Chinese Spoken Language Processing, ISCSLP 2006, held in Singapore in December 2006, colocated with ICCPOL 2006, the 21st International Conference on Computer Processing of Oriental Languages. The 74 revised full papers presented together with 5 invited papers were carefully reviewed and selected from 183 submissions. The papers are organized in topical sections on topics in speech science, speech analysis, speech synthesis and generation, speech enhancement, acoustic modeling for automatic speech recognition, robust speech recognition, speech adaptation/normalization, general topics in speech recognition, large vocabulary continuous speech recognition, multilingual recognition and identification, speaker recognition and characterization, spoken language understanding, human language acquisition, development and learning, spoken and multimodal dialog systems, speech data mining and document retrieval, machine translation of speech, as well as spoken language resources and annotation.

Table of Contents

Interactive computer aids for acquiring proficiency in Mandarin	p. 1
The affective and pragmatic coding of prosody	p. 13
Challenges in machine translation	p. 15
Automatic indexing and retrieval of large broadcast news video collections - the TRECVID experience	p. 16
An HMM-based approach to flexible speech synthesis	p. 17
Text information extraction and retrieval	p. 18
Mechanisms of question intonation in Mandarin	p. 19
Comparison of perceived prosodic boundaries and global characteristics of voice fundamental frequency contours in Mandarin speech	p. 31
Linguistic markings of units in spontaneous Mandarin	p. 43
Phonetic and phonological analysis of focal accents of disyllabic words in standard Chinese	p. 55
Focus, lexical stress and boundary tone : interaction of three prosodic features	p. 67
A robust voice activity detection based on noise eigenspace projection	p. 76
Pitch mean based frequency warping	p. 87
A study of knowledge-based features for obstruent detection and classification in continuous Mandarin speech	p. 95
Speaker-and-environment change detection in broadcast news using maximum divergence common component GMM	p. 106
UBM based speaker segmentation and clustering for 2-speaker detection	p. 116
Design of cubic spline wavelet for open set speaker classification in Marathi	p. 126
Rhythmic organization of Mandarin utterances - a two-stage process	p. 138
Prosodic boundary prediction based on maximum entropy model with error-driven modification	p. 149
Prosodic words prediction from lexicon words with CRF and TBL joint method	p. 161
Prosodic word prediction using a maximum entropy approach	p. 169
Predicting prosody from text	p. 179
Nonlinear emotional prosody generation and annotation	p. 189
A unified framework for text analysis in Chinese TTS	p. 200
Speech synthesis based on a physiological articulatory model	p. 211
An HMM-based Mandarin Chinese text-to-speech system	p. 223
HMM-based emotional speech synthesis using average emotion model	p. 233
A Hakka text-to-speech system	p. 241
Adaptive null-forming algorithm with auditory sub-bands	p. 248
Multi-channel noise reduction in noisy environments	p. 258
Minimum phone error (MPE) model and feature training on Mandarin broadcast news task	p. 270
State-dependent phoneme-based model merging for dialectal Chinese speech recognition	p. 282
Non-uniform kernel allocation based parsimonious HMM	p. 294
Consistent modeling of the static and time-derivative cepstrums for speech recognition using HSPTM	p. 303
Vector autoregressive model for missing feature reconstruction	p. 315
Auditory contrast spectrum for robust speech recognition	p. 325
Signal trajectory based noise compensation for robust speech recognition	p. 335
An HMM compensation approach using unscented transformation for noisy speech recognition	p. 346
Noisy speech recognition performance of discriminative HMMs	p. 358
Distributed speech recognition of Mandarin digits string	p. 370
Unsupervised speaker adaptation using reference speaker weighting	p. 380
Automatic construction of regression class tree for MLLR via model-based hierarchical clustering	p. 390
General topics in speech recognition a minimum boundary error framework for automatic phonetic segmentation	p. 399
Advances in Mandarin broadcast speech transcription at IBM under the DARPA GALE program	p. 410
Improved large vocabulary continuous Chinese speech recognition by character-based consensus networks	p. 422
All-path decoding algorithm for segmental based speech recognition	p. 435
Improved Mandarin speech recognition by lattice rescoring with enhanced tone models	p. 445
On using entropy information to improve posterior probability-based confidence measures	p. 454
Vietnamese automatic speech recognition : the FLaVoR approach	p. 464
Language identification by using syllable-based duration classification on code-switching speech	p. 475
CCC speaker recognition evaluation 2006 : overview, methods, data, results and perspective	p. 485
The IIR submission to CSLP 2006 speaker recognition evaluation	p. 494
A novel alternative hypothesis characterization using kernel classifiers for LLR-based speaker verification	p. 506
Speaker verification using complementary information from vocal source and vocal tract	p. 518
ISCSLP SE evaluation, UVA-CSöes system description. A system based on ANNs	p. 529
Evaluation of EMD-based speaker recognition using ISCSLP2006 Chinese speaker recognition evaluation corpus	p. 539
Integrating complementary features with a confidence measure for speaker identification	p. 549
Discriminative transformation for sufficient adaptation in text-independent speaker verification	p. 558
Fusion of acoustic and tokenization features for speaker recognition	p. 566
Contextual maximum entropy model for edit disfluency detection of spontaneous speech	p. 578
Automatic detection of tone mispronunciation in Mandarin	p. 590
Towards automatic tone correction in non-native Mandarin	p. 602
A corpus-based approach for cooperative response generation in a dialog system	p. 614
A Cantonese speech-driven talking face using translingual audio-to-visual conversion	p. 627
The implementation of service enabling with spoken language of a multi-modal system ozone	p. 640
Spoken correction for Chinese text entry	p. 648
Extractive Chinese spoken document summarization using probabilistic ranking models	p. 660
Meeting segmentation using two-layer cascaded subband filters	p. 672
A multi-layered summarization system for multi-media archives by understanding and structuring of Chinese spoken documents	p. 683
Initial experiments on automatic story segmentation in Chinese spoken documents using lexical cohesion of extracted named entities	p. 693
Some improvements in phrase-based statistical machine translation	p. 704
Automatic spoken language translation template acquisition based on boosting structure extraction and alignment	p. 712
HKUST/MTS : a very large scale Mandarin telephone speech corpus	p. 724
The paradigm for creating multi-lingual text-to-speech voice databases	p. 736
Multilingual speech corpora for TTS system development	p. 748
Construct trilingual parallel corpus on demand	p. 760
The contribution of lexical resources to natural language processing of CJK languages	p. 768
Multilingual spoken language corpus development for communication research	p. 781
Development of multi-lingual spoken corpora of Indian languages	p. 792
Table of Contents provided by Blackwell. All Rights Reserved.