Table of Contents

• Welcome message from the technical program chairsBrian Mak, Bin Ma. [doi]
• Welcome message from the conference chairHelen M. Meng. [doi]
• Alternative hypothesis generation using a weighted kernel feature matrix for ASR substitution error correctionChao-Hong Liu, Chung-Hsien Wu, David Sarwono. 1-5 [doi]
• Speaker-ensemble hidden Markov modeling for automatic speech recognitionGuoli Ye, Brian Mak. 6-10 [doi]
• A synchronized pruning composition algorithm of weighted finite state transducers for large vocabulary speech recognitionZhiyang He, Ping Lv, Wei Li, Ji Wu. 11-15 [doi]
• Context dependant phone mapping for cross-lingual acoustic modelingVan Hai Do, Xiong Xiao, Engsiong Chng, Haizhou Li. 16-20 [doi]
• A comparative study of fMPE and RDLT approaches to LVCSRJian Xu, Zhi-Jie Yan, Qiang Huo. 21-24 [doi]
• A cross-dialect comparison of vowel dispersion and vowel variabilityWai-Sum Lee. 25-29 [doi]
• Analyzing semantic orientation of terms using Affinity PropagationYan Li, Si Li, Weiran Xu, Jun Guo. 30-34 [doi]
• Effects of excitation spread on the intelligibility of Mandarin speech in cochlear implant simulationsFei Chen, Tian Guan, Lena L. N. Wong. 35-39 [doi]
• Acoustic and articulatory analysis on Japanese vowels in emotional speechMengxue Cao, Aijun Li, Qiang Fang, Jianguo Wei, Chan Song, Jianwu Dang. 40-44 [doi]
• Articulatory and spectral characteristics of Cantonese vowelsWai-Sum Lee. 45-49 [doi]
• Exploring mutual information for GMM-based spectral conversionHsin-Te Hwang, Yu Tsao, Hsin-Min Wang, Yih-Ru Wang, Sin-Horng Chen. 50-54 [doi]
• Incorporating dynamic features into minimum generation error training for HMM-based speech synthesisDuy Khanh Ninh, Masanori Morise, Yoichi Yamashita. 55-59 [doi]
• Cross validation and Minimum Generation Error for improved model clustering in HMM-based TTSFeng-Long Xie, Yi-Jian Wu, Frank K. Soong. 60-63 [doi]
• Perceptual clustering based unit selection optimization for concatenative text-to-speech synthesisTao Jiang, Zhiyong Wu, Jia Jia, Lianhong Cai. 64-68 [doi]
• Voice conversion using Bayesian mixture of Probabilistic Linear Regressions and dynamic kernel featuresNa Li, Yu Qiao. 69-73 [doi]
• Effective sentence selection based on phone/model coverage maximization for speaker adaptation in HMM-based speech synthesisCheng-Hsien Lin, Po-Kai Huang, Cheng-Yuan Lin, Chih-Chung Kuo. 74-78 [doi]
• Hierarchical prosodic pattern selection based on Fujisaki model for natural mandarin speech synthesisYi-Chin Huang, Chung-Hsien Wu, Sz-Ting Weng. 79-83 [doi]
• Cross-stream dependency modeling using continuous F0 model for HMM-based speech synthesisXin Wang, Zhen-Hua Ling, Li-Rong Dai. 84-87 [doi]
• Resonance-based spectral deformation in HMM-based speech synthesisJinfu Ni, Yoshinori Shiga, Hisashi Kawai, Hideki Kashioka. 88-92 [doi]
• Detection and emphatic realization of contrastive word pairs for expressive text-to-speech synthesisChunrong Li, Zhiyong Wu, Fanbo Meng, Helen M. Meng, Lianhong Cai. 93-97 [doi]
• Spoken term detection for OOV terms based on triphone confusion matrixYong Xu, Wu Guo, Shan Su, Li-Rong Dai. 98-102 [doi]
• Hierarchical clustering and robust identification for block-based autoregressive speech parameter estimationRuofei Chen, Cheung-fat Chan. 103-107 [doi]
• Phonotactic spoken language recognition: Using diversely adapted acoustic models in parallel phone recognizersCheung Chi Leung, Bin Ma, Haizhou Li. 108-111 [doi]
• A new confidence measure combining Hidden Markov Models and Artificial Neural Networks of phonemes for effective keyword spottingSu Jun Leow, Tze Siong Lau, Alvina Goh, Han Meng Peh, Teck Khim Ng, Sabato Marco Siniscalchi, Chin-Hui Lee. 112-116 [doi]
• Two objective measures for speech distortion and noise reduction evaluation of enhanced speech signalsHuijun Ding, Tan Lee, Ing Yann Soon. 117-121 [doi]
• Synthesized stereo-based stochastic mapping with data selection for robust speech recognitionJun Du, Qiang Huo. 122-125 [doi]
• TDOA information based vad for robust speech recognition in directional and diffuse noise fieldKuan-Lang Huang, Tai-Shih Chi. 126-130 [doi]
• An analysis of vector Taylor series model compensation for non-stationary noise in speech recognitionDuc Hoang Ha Nguyen, Xiong Xiao, Chng Eng Siong, Haizhou Li. 131-135 [doi]
• Structured modeling based on generalized variable parameter HMMs and speaker adaptationYang Li, Xunying Liu, Lan Wang. 136-140 [doi]
• A study on cepstral sub-band normalization for robust ASRSyu-Siang Wang, Jeih-Weih Hung, Yu Tsao. 141-145 [doi]
• Statistical modification based post-filtering technique for HMM-based speech synthesisZhengqi Wen, Jianhua Tao, Hao Che. 146-149 [doi]
• A study of F0 modelling and generation with lyrics and shape characterization for singing voice synthesisSiu Wa Lee, Minghui Dong, Haizhou Li. 150-154 [doi]
• Experiments on unsupervised statistical parametric speech synthesisJinfu Ni, Yoshinori Shiga, Hisashi Kawai, Hideki Kashioka. 155-159 [doi]
• Improved unit selection speech synthesis method utilizing subjective evaluation results on synthetic speechXian-Jun Xia, Zhen-Hua Ling, Chen-Yu Yang, Li-Rong Dai. 160-164 [doi]
• A unified trajectory tiling approach to high quality TTS and cross-lingual voice transformationYao Qian, Frank K. Soong. 165-169 [doi]
• mENUNCIATE: Development of a computer-aided pronunciation training system on a cross-platform framework for mobile, speech-enabled application developmentPengfei Liu, Ka-Wa Yuen, Wai-Kim Leung, Helen M. Meng. 170-173 [doi]
• Analysis on mispronunciations in CAPT based on computational speech perceptionJia Jia, Wai-Kim Leung, Ye Tian, Lianhong Cai, Helen M. Meng. 174-178 [doi]
• Perceptually-motivated assessment of automatically detected lexical stress in L2 learners' speechKun Li, Helen M. Meng. 179-183 [doi]
• Improve mispronunciation detection with Tandem featureHua Yuan, Junhong Zhao, Jia Liu. 184-187 [doi]
• Bayesian nonparametric language modelsYing-Lang Chang, Jen-Tzung Chien. 188-192 [doi]
• Phrase-based data selection for language model adaptation in spoken language translationShixiang Lu, Wei Wei, Xiaoyin Fu, Lichun Fan, Bo Xu. 193-196 [doi]
• Collecting sentences from web resources for constructing spontaneous Chinese language modelXinhui Hu, Youzheng Wu, Shigeki Matsuda, Chiori Hori, Hideki Kashioka. 197-200 [doi]
• Controlling the tradeoff property in a regularization framework for noise reductionXugang Lu, Masashi Unoki, Shigeki Matsuda, Chiori Hori, Hideki Kashioka. 201-205 [doi]
• A fast two-microphone noise reduction algorithm based on power level ratio for mobile phoneJian Zhang, Risheng Xia, Zhonghua Fu, Junfeng Li, YongHong Yan. 206-209 [doi]
• The lossless adaptive arithmetic coding based on context for ITU-T G.719 at variable rateXuan Ji, Jing Wang, Hailong He, Jingming Kuang. 210-214 [doi]
• Unified denoising and dereverberation method used in restoration of MTF-based power envelopeMasashi Unoki, Xugang Lu. 215-219 [doi]
• Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensationChen-Yu Yang, Georgina Brown, Liang Lu, Junichi Yamagishi, Simon King. 220-223 [doi]
• Power-normalized PLP (PNPLP) feature for robust speech recognitionLichun Fan, Dengfeng Ke, Xiaoyin Fu, Shixiang Lu, Bo Xu. 224-228 [doi]
• A feature-transform based approach to unsupervised task adaptation and personalizationJian Xu, Zhi-Jie Yan, Qiang Huo. 229-232 [doi]
• Keyword-specific normalization based keyword spotting for spontaneous speechWeifeng Li, Qingmin Liao. 233-237 [doi]
• Enhanced lengthening cancellation using bidirectional pitch similarity alignment for spontaneous speechPo-Yi Shih, Bo-Wei Chen, Jhing-Fa Wang, Jhing-Wei Wu. 238-242 [doi]
• Information allocation and prosodic expressiveness in continuous speech: A Mandarin cross-genre analysisChiu-yu Tseng, Chao-yu Su. 243-246 [doi]
• Automatic pitch accent detection using auto-context with acoustic featuresJunhong Zhao, Weiqiang Zhang, Hua Yuan, Jia Liu, Shanhong Xia. 247-251 [doi]
• An improved tone labeling and prediction method with non-uniform segmentation of F0 contourXingyu Na, Xiang Xie, Jingming Kuang, YaLing He. 252-255 [doi]
• Break index labeling of mandarin text via syntactic-to-prosodic tree mappingXiaotian Zhang, Yao Qian, Hai Zhao, Frank K. Soong. 256-260 [doi]
• Prosody-based sentence boundary detection in Chinese broadcast newsLei Xie, Chenglin Xu, Xiaoxuan Wang. 261-265 [doi]
• Pitch accent detection and prediction with DCT features and CRF modelWenping Hu, Yao Qian, Frank K. Soong. 266-270 [doi]
• More targets? Simulating emotional intonation of mandarin with PENTAAijun Li, Qiang Fang, Yuan Jia, Jianwu Dang. 271-275 [doi]
• A syllable-based prosody modeling for L1 and L2 English speechesWei-Fan Chen, Chin-Kuan Kuo, Yih-Ru Wang, Sin-Horng Chen. 281-285 [doi]
• A simple and effective pitch re-estimation method for rich prosody and speaking styles in HMM-based speech synthesisCheng-Yuan Lin, Chien-Hung Huang, Chih-Chung Kuo. 286-290 [doi]
• Diachronic contrastive analysis on read speech in broadcast news: Evidence from pitch and durationYu Zou, Yan Wang, Wei He. 291-295 [doi]
• Phonetic realization of accent from Chinese English learners in various dialectal regionsYuan Jia, Aijun Li. 296-300 [doi]
• Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modelingJia Pan, Cong Liu, Zhiguo Wang, Yu Hu, Hui Jiang 0001. 301-305 [doi]
• An improved steady segment based decoding algorithm by using response probability for LVCSRZhanlei Yang, Wenju Liu, Hao Chao. 306-310 [doi]
• Acoustic space partition based on broad phonetic class for ensemble acoustic modelingXugang Lu, Yu Tsao, Shigeki Matsuda, Chiori Hori, Hideki Kashioka. 311-314 [doi]
• A study on cross-language knowledge integration in Mandarin LVCSRChen-Yu Chiang, Sabato Marco Siniscalchi, Yih-Ru Wang, Sin-Horng Chen, Chin-Hui Lee. 315-319 [doi]
• Minimum Phone Error model training on merged acoustic units for transcribing bilingual code-switched speechChing-feng Yeh, Yiu-Chang Lin, Lin-Shan Lee. 320-324 [doi]
• Acoustic modeling for native and non-native Mandarin speech recognitionXin Chen, Jian Cheng. 325-329 [doi]
• Intra-conversation intra-speaker variability compensation for speaker clusteringKui Wu, Yan Song, Wu Guo, Li-Rong Dai. 330-334 [doi]
• Alleviating the small sample-size problem in i-vector based speaker verificationWei Rao, Man-Wai Mak. 335-339 [doi]
• Text-Dependent Speaker Recognition with long-term features based on functional data analysisChenhao Zhang, Thomas Fang Zheng, Ruxin Chen. 340-344 [doi]
• Efficient feature extraction of speaker identification using phoneme mean F-ratio for ChineseChen Zhao, Hongcui Wang, Songgun Hyon, Jianguo Wei, Jianwu Dang. 345-348 [doi]
• Discriminant local information distance preserving projection for text-independent speaker recognitionLiang He, Jia Li. 349-352 [doi]
• Acoustic analysis of disguised voices with raised and lowered pitchCuiling Zhang. 353-357 [doi]
• Boundary-expanding locality sensitive hashingQiang Wang, Zhiyuan Guo, Gang Liu, Jun Guo. 358-362 [doi]
• Adaptive named entity recognition based on conditional random fields with automatic updated dynamic gazetteersXixin Wu, Zhiyong Wu, Jia Jia, Lianhong Cai. 363-367 [doi]
• Nesting hierarchical phrase-based model for speech-to-speech translationXiaoyin Fu, Wei Wei, Lichun Fan, Shixiang Lu, Bo Xu. 368-372 [doi]
• A phone segmentation method and its evaluation on Mandarin speech corpusDac-Thang Hoang, Hsiao-Chuan Wang. 373-377 [doi]
• A hybrid fragment / syllable-based system for improved OOV term detectionYong Xu, Wu Guo, Li-Rong Dai. 378-382 [doi]
• Tongue shape synthesis based on Active Shape ModelChan Song, Jianguo Wei, Qiang Fang, Shen Liu, Yuguang Wang, Jianwu Dang. 383-386 [doi]
• Perceptual similarity between audio clips and feature selection for its measurementQinghua Wu, Xiao-lei Zhang, Ping Lv, Ji Wu. 387-391 [doi]
• Self documentation of endangered languagesSagun Dhakhwa, Jens Allwood. 392-395 [doi]
• Reconstruction of vocal tract based on multi-source image informationSong Wang, Shen Liu, Jianguo Wei, Qiang Fang, Jianwu Dang. 396-399 [doi]
• Robust voice activity detection using empirical mode decomposition and modulation spectrum analysisYasuaki Kanai, Masashi Unoki. 400-404 [doi]
• A real-time tone enhancement method for continuous Mandarin speechesYe Tian, Jia Jia, Yongxin Wang, Lianhong Cai. 405-408 [doi]
• Preliminary study on the interlanguage speech intelligibility benefit for English-Mandarin bilingual l2 learnersGuo Li, Peggy Mok. 409-412 [doi]
• Detailed morphological analysis of mandarin sustained steady vowelsYuguang Wang, Hongcui Wang, Jiaqi Gao, Jianguo Wei, Jianwu Dang. 413-416 [doi]
• Effects of carriers on Mandarin tone categorical perceptionDazuo Wang, Xiuxiu Wang, Gang Peng. 417-421 [doi]
• Tones in whispered MandarinBin Li, Rong Rong. 422-425 [doi]
• A study on the coarticulation of bi-syllabic words in ChineseMaolin Wang, Shengnan Xiong, Jiayun Li, Ziyu Xiong. 426-430 [doi]
• A comparative study of perception of tone 2 and tone 3 in Mandarin by native speakers and Japanese learnersTing Zou, Jinsong Zhang, Wen Cao. 431-435 [doi]
• A preliminary investigation of the third tone sandhi in standard Chinese with a prosodic corpusHongwei Ding, Daniel Hirst. 436-439 [doi]
• Locus of orthographic facilitation effect in spoken word production: Evidence from cantonese ChineseI.-Fan Su, Sin-Ting Yeung, Brendan S. Weekes, Sam-Po Law. 440-444 [doi]
• The temporal effect of speaking rate, focus and prosody in ChineseMaolin Wang, Wei Shi, Ruixian Huang, Ziyu Xiong. 445-449 [doi]
• How to describe speech emotion more completely - An investigation on Chinese broadcast news speechYingying Gao, Weibin Zhu. 450-453 [doi]
• The coarticulation resistance of consonants in standard Chinese - An electropalatographic and acoustic studyYinghao Li, Jinghua Zhang, Jiangping Kong. 454-458 [doi]