Technical Program
| Time/Date | Dec 5 (Wed) | ..... | Time/Date | Dec 6 (Thu) | Dec 7 (Fri) | Dec 8 (Sat) |
|---|---|---|---|---|---|---|
| 8:00 - 8:30 | Registration | Registration | ||||
| 8:30 - 9:00 | Opening | |||||
| 9:00 - 10:00 | Keynote Speech #1 Mark Gales |
Keynote Speech #2 Fan-Gang Zeng |
Keynote Speech #3 Daniel Hirst |
|||
| 10:00 - 10:30 | MORNING COFFEE BREAK | |||||
| 12:00 - 17:00 | Registration | 10:30 - 11:30 | O1/P1 | O4/P4 | Keynote Speech #4 Eric Chang |
|
| 13:00 - 14:15 | Tutorial #1 Khe Chai Sim |
11:30 - 12:10 | ISCA SIG-CSLP General Assembly & Closing |
|||
| BREAK | 12:10 - 14:00 | LUNCH | ||||
| 14:30 - 15:45 | Tutorial #2 Tomoki Toda |
14:00 - 15:40 | O2/P2 | O5/P5 | ||
| BREAK | 15:40 - 16:10 | AFTERNOON COFFEE BREAK | ||||
| 16:00 - 17:15 | Tutorial #3 Dong Yu |
16:10 - 17:50 | O3/P3 | O6/P6 | ||
| 19:00 - 21:00 | BANQUET | |||||
Remarks:
| Oral Session | Oral Session Title | Session Chair |
|---|---|---|
| O1 | Automatic Speech Recognition | Dr. Kate Knill |
| O2 | Phonetics, Phonology, Linguistics, and Speech Analysis | Prof. Chiuyu Tseng |
| O3 | Speech Synthesis and Voice Conversion | Prof. Kai Yu |
| O4 | Speech Synthesis | Prof. Tomoki Toda |
| O5 | General Topics on ASR | Prof. Khe Chai Sim |
| O6 | Robust Speech Recognition | Dr. Qiang Huo |
| Poster Session | Poster Session Title | Session Chair |
|---|---|---|
| P1 | Speech Synthesis, Pronunciation Learning, and Language Modeling | Dr. Jianhua Tao |
| P2 | Speech Enhancement and Robust ASR | Prof. Sin-Horng Chen |
| P3 | Speech Prosody | Prof. Hsiao-chuan Wang |
| P4 | Speech and Speaker Recognition | Dr. Hsin-Min Wang |
| P5 | General Topics in Spoken Language Processing | Prof. C. F. Chan |
| P6 | Phonetics and Phonology; Speech Production and Perception | Prof. Aijun Li |
| Submission ID | Section | Conference ID | Time | Venue | Paper Title | Author Names |
|---|---|---|---|---|---|---|
| 52 | O1 | O1.1 | Dec 6 10:30-10:50 | Chamber 1 | Alternative Hypothesis Generation Using A Weighted Kernel Feature Matrix For ASR Substitution Error Correction | Chao-Hong Liu, Chung-Hsien Wu*, David Sarwono, National Cheng Kung University |
| 141 | O1 | O1.2 | Dec 6 10:50-11:10 | Chamber 1 | Speaker-Ensemble Hidden Markov Modeling For Automatic Speech Recognition | Guoli YE*, HKUST; Brian Mak, The Hong Kong University of Science and Technology |
| 50 | O1 | O1.3 | Dec 6 11:10-11:30 | Chamber 1 | A Synchronized Pruning Composition Algorithm Of Weighted Finite State Transducers For Large Vocabulary Speech Recognition | Zhiyang He*, Ping Lv, Tsinghua-iFlytek Joint Lab; Wei Li, Ji Wu, Tsinghua University |
| 84 | O1 | O1.4 | Dec 6 11:30-11:50 | Chamber 1 | Context Dependent Phone Mapping For Cross-Lingual Acoustic Modeling | Van Hai Do*, Xiong Xiao, Eng Siong Chng, Haizhou Li, Nanyang Technological University, Singapore |
| 107 | O1 | O1.5 | Dec 6 11:50-12:10 | Chamber 1 | A Comparative Study Of FMPE And RDLT Approaches To LVCSR | Jian Xu*, Univ. of Sci. & Tech. of China; Zhijie Yan, Microsoft Research Asia ; Qiang Huo, "Microsoft Research Asia, Beijing" |
| 21 | O2 | O2.1 | Dec 6 14:00-14:20 | Chamber 1 | A Cross-Dialect Comparison Of Vowel Dispersion And Vowel Variability | Wai-Sum Lee*, City University of Hong Kong |
| 79 | O2 | O2.2 | Dec 6 14:20-14:40 | Chamber 1 | Analyzing Semantic Orientation Of Terms Using Affinity Propagation | Yan Li*, Si Li, Weiran Xu, Jun Guo, Beijing University of Posts and Telecommunications |
| 91 | O2 | O2.3 | Dec 6 14:40-15:00 | Chamber 1 | Effects Of Excitation Spread On The Intelligibility Of Mandarin Speech In Cochlear Implant Simulations | Fei Chen*, The University of Hong Kong; Tian Guan,Tsinghua University; Lena L. N. Wong,The University of Hong Kong |
| 113 | O2 | O2.4 | Dec 6 15:00-15:20 | Chamber 1 | Acoustic And Articulatory Analysis On Japanese Vowels In Emotional Speech | Mengxue CAO*, Institute of Linguistics, CASS; Ai-Jun Li, Chinese Academy of Social Sciences, Beijing; Qiang FANG, Institute of Linguistics, CASS; Jianguo WEI, Chan SONG, Jianwu DANG, School of Computer Science, TJU |
| 48 | O2 | O2.5 | Dec 6 15:20-15:40 | Chamber 1 | Articulatory And Spectral Characteristics Of Cantonese Vowels | Wai-Sum Lee*, City University of Hong Kong |
| 55 | O3 | O3.1 | Dec 6 16:10-16:30 | Chamber 1 | Exploring Mutual Information For GMM-Based Spectral Conversion | Hsin-Te Hwang*, Dept. of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan; Yu Tsao, Academia Sinica; Hsin-Min Wang, Academia Sinica, Taipei; Yih-Ru Wang, Sin-Horng Chen, National Chiao Tung University, Hsinchu, Taiwan |
| 67 | O3 | O3.2 | Dec 6 16:30-16:50 | Chamber 1 | Incorporating Dynamic Features Into Minimum Generation Error Training For Hmm-Based Speech Synthesis | Duy Khanh Ninh*, Ritsumeikan University; Masanori Morise, Ritsumeikan University; Yoichi Yamashita, Ritsumeikan University |
| 26 | O3 | O3.3 | Dec 6 16:50-17:10 | Chamber 1 | Cross Validation And Minimum Generation Error For Improved Model Clustering In Hmm-Based TTS | Feng-Long Xie*, Harbin Institute of Technology; Yi-Jian Wu, ; Frank Soong, J15Microsoft Research Asia, Beijing |
| 71 | O3 | O3.4 | Dec 6 17:10-17:30 | Chamber 1 | Perceptual Clustering Based Unit Selection Optimization For Concatenative Text-To-Speech Synthesis | Tao Jiang*, Tsinghua University, Shenzhen; Zhiyong Wu, Tsinghua University, Shenzhen; Jia Jia, Tsinghua University, Shenzhen; Lian-Hong Cai, "Tsinghua University, Beijing" |
| 124 | O3 | O3.5 | Dec 6 17:30-17:50 | Chamber 1 | Voice Conversion Using Bayesian Mixture Of Probabilistic Linear Regressions And Dynamic Kernel Features | Na Li*, Northwestern Polytechnical Uni; Qiao Yu, Shenzhen key lab of CVPR, Shenzhen Institutes of Advanced Technology; Zhifeng Li, The Chinese University of Hong Kong |
| 43 | O4 | O4.1 | Dec 7 10:30-10:50 | Chamber 1 | Effective Sentence Selection Based On Phone/Model Coverage Maximization For Speaker Adaptation In Hmm-Based Speech Synthesis | Cheng Hsien Lin*, Po Kai Huang, Cheng-Yuan Lin, Chih Chung Kuo, ITRI, Taiwan |
| 149 | O4 | O4.2 | Dec 7 10:50-11:10 | Chamber 1 | Hierarchical Prosodic Pattern Selection Based On Fujisaki Model For Natural Mandarin Speech Synthesis | Yi-Chin Huang, Chung-Hsien Wu*, Sz-Ting Weng, National Cheng Kung University |
| 20 | O4 | O4.3 | Dec 7 11:10-11:30 | Chamber 1 | Cross-Stream Dependency Modeling Using Continuous F0 Model For Hmm-Based Speech Synthesis | Xin Wang*, Zhen-Hua Ling, Li-Rong Dai, USTC iFLYTEK Speech Lab |
| 56 | O4 | O4.4 | Dec 7 11:30-11:50 | Chamber 1 | Resonance-Based Spectral Deformation In Hmm-Based Speech Synthesis | Jinfu Ni*, NICT; Yoshinori Shiga, NICT; Hisashi Kawai, KDDI; Hideki Kashioka, NICT |
| 77 | O4 | O4.5 | Dec 7 11:50-12:10 | Chamber 1 | Detection And Emphatic Realization Of Contrastive Word Pairs For Expressive Text-To-Speech Synthesis | Chunrong Li*, Zhiyong Wu, Tsinghua University; Fanbo Meng, Tsinghua National Laboratory for Information Science and Technology (TNList); Helen Meng, The Chinese University of HK; Lian-Hong Cai, Tsinghua University, Beijing |
| 58 | O5 | O5.1 | Dec 7 14:00-14:20 | Chamber 1 | Spoken Term Detection For OOV Terms Based On Triphone Confusion Matrix | Yong Xu*, Wu Guo, Shan Su, Li-Rong Dai, University of Science and Technology of China, Hefei+J36 |
| 60 | O5 | O5.2 | Dec 7 14:20-14:40 | Chamber 1 | Hierarchical Clustering And Robust Identification For Block-Based Autoregressive Speech Parameter Estimation | Ruofei Chen*, Cheung Fat Chan, City University of Hong Kong, Hong Kong |
| 103 | O5 | O5.3 | Dec 7 14:40-15:00 | Chamber 1 | Phonotactic Spoken Language Recognition: Using Diversely Adapted Acoustic Models In Parallel Phone Recognizers | Cheung-Chi LEUNG*, I2R, A*STAR; Bin Ma, Institute for Infocomm Research, Singapore; Haizhou Li, Institute for Infocomm Research, Singapore |
| 18 | O5 | O5.4 | Dec 7 15:00-15:20 | Chamber 1 | A New Confidence Measure Combining Hidden Markov Models And Artificial Neural Networks Of Phonemes For Effective Keyword Spotting | Su Jun Leow, Nanyang Technological University; Tze Siong Lau, ; Alvina Goh*, Han Meng Peh, Teck Khim Ng,**National University of Singapore; Sabato Marco Siniscalchi, Kore University of Enna; Chin-Hui Lee, Georgia Institute of Technology, USA |
| 70 | O5 | O5.5 | Dec 7 15:20-15:40 | Chamber 1 | Two Objective Measures For Speech Distortion And Noise Reduction Evaluation Of Enhanced Speech Signals | Huijun Ding*, CUHK; Tan Lee, CUHK; Ing Yann Soon, Nanyang Technological University, Singapore |
| 158 | O6 | O6.1 | Dec 7 16:10-16:30 | Chamber 1 | Synthesized Stereo-Based Stochastic Mapping With Data Selection For Robust Speech Recognition | Jun Du*, Microsoft Research Asia, Beijing ; Qiang Huo, Microsoft Research Asia, Beijing |
| 110 | O6 | O6.2 | Dec 7 16:30-16:50 | Chamber 1 | TODA Information Based VAD For Robust Speech Recognition In Directional And Diffuse Noise Field | Kuan-Lang Huang*, NCTU, R.O.C.; Tai-Shih Chi, NCTU, R.O.C. |
| 94 | O6 | O6.3 | Dec 7 16:50-17:10 | Chamber 1 | An Analysis Of Vector Taylor Series Model Compensation For Non-Stationary Noise In Speech Recognition | Duc Hoang Ha Nguyen*, Xiong Xiao, Eng Siong Chng, Haizhou Li, Nanyang Technological University |
| 131 | O6 | O6.4 | Dec 7 17:10-17:30 | Chamber 1 | Structured Modeling Based On Generalized Variable Parameter HMMs And Speaker Adaptation | Yang Li*, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Xunying Liu, Cambridge University Engineering Dept; Lan Wang, Institutes of Advanced Technology, Chinese Academy of Sciences |
| 64 | O6 | O6.5 | Dec 7 17:30-17:50 | Chamber 1 | A Study On Cepstral Subband Normalization For Robust ASR | Syu-Siang Wang*, Academia Sinica; Jeih-Weih Hung, National Chi Nan University ; Yu Tsao, Academia Sinica |
| 19 | P1 | P1.1 | Dec 6 10:30-12:10 | Chamber 3 | Statistical Modification Based Postfilter Technique For Hmm-Based Speech Synthesis | Zhengqi Wen*, Jianhua Tao, Hao Che, Chinese Academy of Sciences |
| 74 | P1 | P1.2 | Dec 6 10:30-12:10 | Chamber 3 | A Study Of F0 Modelling And Generation With Lyrics And Shape Characterization For Singing Voice Synthesis | Siu Wa Yvonne Lee*, Minghui Dong, Haizhou Li, Institute for Infocomm Research, Singapore |
| 115 | P1 | P1.3 | Dec 6 10:30-12:10 | Chamber 3 | Experiments On Unsupervised Statistical Parametric Speech Synthesis | Jinfu Ni*, NICT; Yoshinori Shiga, NICT; Hisashi Kawai, KDDI; Hideki Kashioka, NICT |
| 127 | P1 | P1.4 | Dec 6 10:30-12:10 | Chamber 3 | Improved Unit Selection Speech Synthesis Method Utilizing Subjective Evaluation Results On Synthetic Speech | Xian-Jun Xia*,Zhen-Hua Ling, Chen-Yu Yang, iFLYTEK Speech Lab, USTC, China; Li-Rong Dai, University of Science and Technology of China, Hefei |
| 98 | P1 | P1.5 | Dec 6 10:30-12:10 | Chamber 3 | A Unified Trajectory Tiling Approach To High Quality TTS And Cross-Lingual Voice Transformation | Yao Qian*, Microsoft Research Asia; Frank Soong, Microsoft Research Asia, Beijing |
| 100 | P1 | P1.6 | Dec 6 10:30-12:10 | Chamber 3 | mENUNCIATE: Development Of A Computer-Aided Pronunciation Training System On A Cross-Platform Framework For Mobile, Speech-Enabled Application Development | Pengfei Liu*, Ka-Wa Yuen, Wai-Kim Leung, Helen Meng, Human-Computer Communications Laboratory, The Chinese University of Hong Kong |
| 138 | P1 | P1.7 | Dec 6 10:30-12:10 | Chamber 3 | Analysis On Mispronunciations In CAPT Based On Computational Speech Perception | Jia Jia*, Tsinghua University; Wai-Kim Leung, Human-Computer Communications Laboratory, The Chinese University of Hong Kong; Ye Tian, Tsinghua University; Lian-Hong Cai, "Tsinghua University, Beijing"; Helen M. Meng, The Chinese University of HK |
| 120 | P1 | P1.8 | Dec 6 10:30-12:10 | Chamber 3 | Perceptually-Motivated Assessment Of Automatically Detected Lexical Stress In L2 Learners' Speech | Kun Li*, Helen Meng, The Chinese University of HK |
| 153 | P1 | P1.9 | Dec 6 10:30-12:10 | Chamber 3 | Improve Mispronunciation Detection With Tandem Feature | Hua Yuan*, Tsinghua University; Junhong Zhao, University of Chinese Academy of Sciences; Jia Liu, "Tsinghua University, Beijing" |
| 29 | P1 | P1.10 | Dec 6 10:30-12:10 | Chamber 3 | Bayesian Nonparametric Language Models | Ying-Lan Chang, Jen-Tzung Chien*, National Chiao Tung University |
| 63 | P1 | P1.11 | Dec 6 10:30-12:10 | Chamber 3 | Phrase-Based Data Selection For Language Model Adaptation In Spoken Language Translation | Shixiang Lu*, Wei Wei, Xiaoyin Fu, Lichun Fan, Bo Xu, Institute of Automation, Chinese Academy of Sciences |
| 171 | P1 | P1.12 | Dec 6 10:30-12:10 | Chamber 3 | Collecting Sentences From Web Resources For Constructing Spontaneous Chinese Language Model | Xinhui Hu*, NICT; Youzheng Wu, NICT; Shigeki Matsuda, NICT; Chiori Hori, NICT; Hideki Kashioka, NICT |
| 89 | P2 | P2.1 | Dec 6 14:00-15:40 | Chamber 3 | Controlling The Tradeoff Property In A Regularization Framework For Noise Reduction | Xugang Lu*, NICT; Masashi Unoki, Japan Advanced Institute of Science and Technology; Matsuda Shigeki, NICT; Chiori Hori, NICT; Hideki Kashioka, NICT |
| 108 | P2 | P2.2 | Dec 6 14:00-15:40 | Chamber 3 | A Fast Two-Microphone Noise Reduction Algorithm Based On Power Level Ratio For Mobile Phone | Jian Zhang*, School of Computer Science, Northwestern Polytechnical University, Xi'an, China; Risheng Xia, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China; ZhongHua Fu, Lei Xie, North Western Polytechnical University, Xian; Junfeng Li, Yonghong Yan, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China |
| 32 | P2 | P2.3 | Dec 6 14:00-15:40 | Chamber 3 | The Lossless Adaptive Arithmetic Coding Based On Context For Itu-T G.719 At Variable Rate | Xuan Ji, Jing Wang, Hailong He, Jingming Kuang, Beijing Institute of Technology |
| 88 | P2 | P2.4 | Dec 6 14:00-15:40 | Chamber 3 | Unified Denoising And Dereverberation Method Used In Restoration Of MTF-Based Power Envelope | Masashi Unoki*, Japan Advanced Institute of Science and Technology; Xugang Lu, NICT |
| 125 | P2 | P2.5 | Dec 6 14:00-15:40 | Chamber 3 | Noise-Robust Whispered Speech Recognition Using A Non-Audible-Murmur Microphone With VTS Compensation | Chen-Yu Yang*, iFly Speech Lab, USTC, China; Georgina Brown, University of Edinburgh; Liang Lu, USTC ; Junichi Yamagishi, University of Edinburgh; Simon King, University of Edinburgh |
| 137 | P2 | P2.6 | Dec 6 14:00-15:40 | Chamber 3 | Power-Normalized PLP (PnPLP) Feature For Robust Speech Recognition | lichun fan*, DengFeng Ke, Xiaoyin Fu, Shixiang Lu, Bo Xu, Institute of Automation, Chinese Academy of Sciences |
| 109 | P2 | P2.7 | Dec 6 14:00-15:40 | Chamber 3 | A Feature-Transform Based Approach To Unsupervised Task Adaptation And Personalization | Jian Xu*, Univ. of Sci. & Tech. of China; Zhijie Yan, Microsoft ; Qiang Huo, Microsoft Research Asia, Beijing |
| 73 | P2 | P2.8 | Dec 7 14:00-15:40 | Chamber 3 | Keyword-Specific Normalization Based Keyword Spotting For Spontaneous Speech | Weifeng Li*, Tsinghua University; Qingmin Liao, Tsinghua University |
| 114 | P2 | P2.9 | Dec 7 14:00-15:40 | Chamber 3 | Enhanced Lengthening Cancellation Using Bidirectional Pitch Similarity Alignment For Spontaneous Speech | Po-Yi Shih*, Bo Wei Chen, Jhing Fa Wang, Jhing-Wei Wu, National Cheng Kung University; |
| 148 | P3 | P3.1 | Dec 6 16:10-17:50 | Chamber 3 | Information Allocation And Prosodic Expressiveness In Continuous Speech: A Mandarin Cross-Genre Analysis | Chiu-yu Tseng*, Phonetics Lab, Institute of Linguistics, Academia sinica; Chao-yu Su, Taiwan International Graduate Program (TIGP), Academia Sinica Taipei, Taiwan |
| 126 | P3 | P3.2 | Dec 6 16:10-17:50 | Chamber 3 | Automatic Pitch Accent Detection Using Auto-Context With Acoustic Features | Junhong Zhao*, IECAS; Wei-Qiang Zhang, TsingHua National Laboratory for Information Science and Technology; Hua Yuan, Tsinghua University; Jia Liu, Tsinghua University, Beijing; ShanHong Xia, IECAS |
| 41 | P3 | P3.3 | Dec 6 16:10-17:50 | Chamber 3 | An Improved Tone Labeling And Prediction Method With Non-Uniform Segmentation Of F0 Contour | Xingyu Na*, Xiang Xie, Jingming Kuang, Beijing Institute of Technology; Yaling He, Eastel Corporation, Beijing |
| 42 | P3 | P3.4 | Dec 6 16:10-17:50 | Chamber 3 | Break Index Labeling Of Mandarin Text Via Syntactic-To-Prosodic Tree Mapping | Xiaotian Zhang*, Shanghai Jiao Tong University; Yao Qian, Microsoft Research Asia; Hai Zhao, Shanghai Jiao Tong University; Frank Soong, Microsoft Research Asia, Beijing |
| 47 | P3 | P3.5 | Dec 6 16:10-17:50 | Chamber 3 | Prosody-Based Sentence Boundary Detection In Chinese Broadcast News | Lei Xie*, Chenglin Xu, Xiaoxuan Wang, Northwestern Polytechnical University, Xi'an |
| 96 | P3 | P3.6 | Dec 6 16:10-17:50 | Chamber 3 | Pitch Accent Detection And Prediction With DCT Features And CRF Model | Wenping Hu*, University of Science and Technology of China; Yao Qian, Microsoft Research Asia; Frank Soong, Microsoft Research Asia, Beijing |
| 165 | P3 | P3.7 | Dec 6 16:10-17:50 | Chamber 3 | More Targets? Simulating Emotional Intonation Of Mandarin With PENTA | Ai-Jun Li*, "Chinese Academy of Social Sciences, Beijing"; Qiang FANG, Institute of Linguistics, CASS; Yuan Jial, Phonetics Lab, Institute of Linguistics, Chinese Academy of Social Sciences; Jianwu Dang, JAIST, Japan |
| 16 | P3 | P3.8 | Dec 6 16:10-17:50 | Chamber 3 | Research On The Pitch Contour And Prosodic Phrase In Mongolian | Ao Min*, Inner Mongolian University; XIONG ziyu, Chinese Academy of Social Sciences; BORJIGIN Bayarmend, Inner Mongolian University |
| 36 | P3 | P3.9 | Dec 6 16:10-17:50 | Chamber 3 | A Syllable-Based Prosody Modeling For L1 And L2 English Speeches | Wei-Fan Chen*, Chin-Kuan Kuo, Yih-Ru Wang, Sin-Horng Chen, National Chiao Tung University, Hsinchu |
| 49 | P3 | P3.10 | Dec 6 16:10-17:50 | Chamber 3 | A Simple And Effective Pitch Re-Estimation Method For Rich Prosody And Speaking Styles In Hmm-Based Speech Synthesis | Cheng-Yuan Lin*, Chien-Hung Huang, Chih Chung Kuo, ITRI, Taiwan |
| 87 | P3 | P3.11 | Dec 6 16:10-17:50 | Chamber 3 | Diachronic Contrastive Analysis On Read Speech In Broadcast News: Evidence From Pitch And Duration | Yu Zou*, Communication University of China; Yan Wang, Communication University of China; Wei He, Communication University of China |
| 166 | P3 | P3.12 | Dec 6 16:10-17:50 | Chamber 3 | Phonetic Realization Of Accent From Chinese English Learners In Various Dialectal Regions | Yuan Jia*, Phonetics Lab, Institute of Linguistics, Chinese Academy of Social Sciences; Ai-Jun Li, Phonetics Lab, Chinese Academy of Social Sciences, Beijing |
| 13 | P4 | P4.1 | Dec 7 10:30-12:10 | Chamber 3 | Investigation Of Deep Neural Networks (DNN) For Large Vocabulary Continuous Speech Recognition: Why DNN Surpasses GMMs In Acoustic Modeling | Jia Pan*, Iflytek Research; Cong Liu, Iflytek Research; ZhiGuo Wang, ; Yu Hu, Iflytek Research; Hui Jiang, York University |
| 129 | P4 | P4.2 | Dec 7 10:30-12:10 | Chamber 3 | An Improved Steady Segment Based Decoding Algorithm By Using Response Probability For LVCSR | Zhanlei Yang*, NLPR, CASIA; Wenju Liu, NLPR, Institute of Automation, Chinese Academy of Sciences; Hao Chao, |
| 90 | P4 | P4.3 | Dec 7 10:30-12:10 | Chamber 3 | Acoustic Space Partition Based On Broad Phonetic Class For Ensemble Acoustic Modeling | Xugang Lu*, NICT; Yu Tsao, Academia Sinica; Matsuda Shigeki, NICT; Chiori Hori, NICT; Hideki Kashioka, NICT |
| 136 | P4 | P4.4 | Dec 7 10:30-12:10 | Chamber 3 | A Study On Cross-Language Knowledge Integration In Mandarin LVCSR | Chen-Yu CHIANG*, National Chiao Tung University; Sabato Marco Siniscalchi, Kore University of Enna ; Yih-Ru Wang, National Chiao Tung University; Sin-Horng Chen, National Chiao Tung University, Hsinchu; Chin-Hui Lee, Georgia Institute of Technology, USA |
| 139 | P4 | P4.5 | Dec 7 10:30-12:10 | Chamber 3 | Minimum Phone Error Training On Merged Acoustic Units For Transcribing Bilingual Code-Switched Speech | Ching-Feng Yeh*, National Taiwan University; Yiu-Chang Lin, National Taiwain University; Lin-Shan Lee, National Taiwan University |
| 161 | P4 | P4.6 | Dec 7 10:30-12:10 | Chamber 3 | Acoustic Modeling For Native And Non-Native Mandarin Speech Recognition | Xin Chen*, Knowledge Technologies, Pearson ; Jian Cheng, Knowledge Technologies, Pearson |
| 37 | P4 | P4.7 | Dec 7 10:30-12:10 | Chamber 3 | Intra-Conversation Intra-Speaker Variability Compensation For Speaker Clustering | Kui Wu*, Yan Song, Wu Guo, Li-Rong Dai, IFly Speech Lab, USTC+J25 |
| 133 | P4 | P4.8 | Dec 7 10:30-12:10 | Chamber 3 | Alleviating The Small Sample-Size Problem In i-Vector Based Speaker Verification | Wei Rao*, The HK Polytechnic University; Man-Wai Mak, HKPolyU |
| 30 | P4 | P4.9 | Dec 7 10:30-12:10 | Chamber 3 | Text-Dependent Speaker Recognition With Long-Term Features Based On Functional Data Analysis | Chenhao Zhang, Fang Zheng*, Tsinghua University; Ruxin Chen, Sony Computer Entertainment America |
| 65 | P4 | P4.10 | Dec 7 10:30-12:10 | Chamber 3 | Efficient Feature Extraction Of Speaker Identification Using Phoneme Mean F-Ratio For Chinese | Chen Zhao*, Hongcui Wang, Songgun Hyon, Jianguo Wei, Tianjin University China ; Jianwu Dang, J41JAIST, Japan |
| 40 | P4 | P4.11 | Dec 7 10:30-12:10 | Chamber 3 | Discriminant Local Information Distance Preserving Projection For Text-Independent Speaker Recognition | Liang He*, Jia Liu, Tsinghua University |
| 105 | P4 | P4.12 | Dec 7 10:30-12:10 | Chamber 3 | Acoustic Analysis Of Disguised Voices With Raised And Lowered Pitch | Cuiling Zhang*, China Criminal Police Univers |
| 33 | P5 | P5.1 | Dec 7 14:00-15:40 | Chamber 3 | Boundary-Expanding Locality Sensitive Hashing | Qiang Wang*, Zhiyuan Guo, Gang Liu, Jun Guo, Beijing University of Posts and Telecommunications |
| 83 | P5 | P5.2 | Dec 7 14:00-15:40 | Chamber 3 | Adaptive Named Entity Recognition Based On Conditional Random Fields With Automatic Updated Dynamic Gazetteers | Xixin Wu*, Tsinghua University; Zhiyong Wu, Tsinghua University; Jia Jia, Tsinghua University; Lian-Hong Cai, Tsinghua University, Beijing |
| 85 | P5 | P5.3 | Dec 7 14:00-15:40 | Chamber 3 | Nesting Hierarchical Phrase-Based Model For Speech-To-Speech Translation | Xiaoyin Fu*, Wei Wei, Lichun Fan, Shixiang Lu, Bo Xu+J53, Institute of Automation, Chinese Academy of Sciences |
| 111 | P5 | P5.4 | Dec 7 14:00-15:40 | Chamber 3 | A Phone Segmentation Method And Its Evaluation On Mandarin Speech Corpus | Dac-Thang Hoang*, National Tsing Hua University; Hsiao-Chuan Wang, National Tsing Hua University |
| 57 | P5 | P5.5 | Dec 7 14:00-15:40 | Chamber 3 | A Hybrid Fragment / Syllable-Based System For Improved OOV Term Detection | Yong Xu*, University of Science and Technology of China; Wu Guo, ; Li-Rong Dai, University of Science and Technology of China, Hefei |
| 152 | P5 | P5.6 | Dec 7 14:00-15:40 | Chamber 3 | Tongue Shape Synthesis Based On Active Shape Model | Chan Song*, Tianjin University; Jianguo WEI, School of Computer Science, TJU; Qiang FANG, Institute of Linguistics, CASS; Shen Liu, Tianjin University; Yuguang Wang, Tianjin University; Jianwu Dang, JAIST, Japan |
| 53 | P5 | P5.7 | Dec 7 14:00-15:40 | Chamber 3 | Perceptual Similarity Between Audio Clips And Feature Selection For Its Measurement | Qing-Hua Wu*, Tsinghua University; Xiao-Lei Zhang, Tsinghua University; Ping Lv, ; Ji Wu, |
| 157 | P5 | P5.8 | Dec 7 14:00-15:40 | Chamber 3 | Self Documentation Of Endangered Languages | "Sagun Dhakhwa*, Centre for Communication & Development Studies, Nepal; Jens Alwood, University of Gothenburg" |
| 143 | P5 | P5.9 | Dec 7 14:00-15:40 | Chamber 3 | Reconstruction Of Vocal Tract Based On Multi-Source Image Information | Song Wang*, Tianjin University; Shen Liu, Tianjin University; Jianguo WEI, School of Computer Science, TJU; Qiang FANG, Institute of Linguistics, CASS; Jianwu Dang, "JAIST, Japan" |
| 119 | P5 | P5.10 | Dec 7 14:00-15:40 | Chamber 3 | Robust Voice Activity Detection Using Empirical Mode Decomposition And Modulation Spectrum Analysis | Yasuaki KANAI*, School of Information Science and Technology; Masashi Unoki, Japan Advanced Institute of Science and Technology |
| 146 | P5 | P5.11 | Dec 6 14:00-15:40 | Chamber 3 | A Real-Time Tone Enhancement Method For Continuous Mandarin Speeches | Ye Tian*, Tsinghua University; Jia Jia, Tsinghua University; Yongxin Wang,Tsinghua University ; Lian-Hong Cai, Tsinghua University, Beijing |
| 68 | P6 | P6.1 | Dec 7 16:10-17:50 | Chamber 3 | A Preliminary Study On The Interlanguage Speech Intelligibility Benefit For English-Mandarin Bilingual L2 Learners | Guo Li, CUHK ; Peggy Mok*, CUHK |
| 75 | P6 | P6.2 | Dec 7 16:10-17:50 | Chamber 3 | Detailed Morphological Analysis Of Mandarin Sustained Steady Vowels | Yuguang Wang*, Tianjin University; Hongcui Wang,Tianjin University ; Jiaqi Gao, Tianjin University; Jianguo Wei, Tianjin University; Jianwu Dang, JAIST, Japan+J48 |
| 97 | P6 | P6.3 | Dec 7 16:10-17:50 | Chamber 3 | Effects Of Carriers On Mandarin Tone Categorical Perception | Wang Dazuo, SIAT; Xiuxiu Wang, Nankai University; Gang Peng* , The Chinese University of HK |
| 154 | P6 | P6.4 | Dec 7 16:10-17:50 | Chamber 3 | Tones In Whispered Mandarin | BIN LI*, CITY UNIVERSITY OF HONG KONG; Rong Rong, Nankai University |
| 15 | P6 | P6.5 | Dec 7 16:10-17:50 | Chamber 3 | A Study On The Coarticulation Of Bi-Syllabic Words In Chinese | Maolin Wang*, Jinan University; Shengnan Xiong, Jinan University; Jiayun Li, Jinan University; Ziyu Xiong, Chinese Academy of Social Sciences |
| 155 | P6 | P6.6 | Dec 7 16:10-17:50 | Chamber 3 | A Comparative Study Of Perception Of Tone 2 And Tone 3 In Mandarin By Native Speakers And Japanese Learners | Ting Zou*, Beijing Language and Culture University; Jinsong Zhang , Beijing Language and Culture University; Wen Cao, Beijing language and culture university |
| 159 | P6 | P6.7 | Dec 7 16:10-17:50 | Chamber 3 | A Preliminary Investigation Of The Third Tone Sandhi In Standard Chinese With A Prosodic Corpus | Hongwei Ding*, Tongji University; Daniel Hirst, CNRS, Laboratoire Parole et Langage & Universite de Provence, France & Tongji University, China |
| 45 | P6 | P6.8 | Dec 7 16:10-17:50 | Chamber 3 | Locus Of Orthographic Facilitation Effect In Spoken Word Production: Evidence From Cantonese Chinese | I-Fan Su*, Sin-Ting Yeung, Brendan S. Weekes, Sam Po Law, University of Hong Kong |
| 59 | P6 | P6.9 | Dec 7 16:10-17:50 | Chamber 3 | The Temporal Effect Of Speaking Rate, Focus And Prosody In Chinese | Maolin Wang*, Jinan University; Wei Shi, Jinan University; Ruixian Huang, Jinan University; Ziyu Xiong, Institute of Linguistics Chinese Academy of Social Sciences Beijing |
| 101 | P6 | P6.10 | Dec 7 16:10-17:50 | Chamber 3 | How To Describe Speech Emotion More Completely- An Investigation On Chinese Broadcast News Speech | Yingying GAO, Beijing Jiaotong University; Weibin ZHU*, Beijing Jiaotong University |
| 162 | P6 | P6.11 | Dec 7 16:10-17:50 | Chamber 3 | The Coarticulation Resistance Of Consonants In Standard Chinese ¨C An Electropalatographic And Acoustic Study | Li Yinghao, Yanbian University; Zhang Jinghua, Yanbian University; Kong Jiangping*, Peking University |