吴志勇

1995年7月-1999年7月，清华大学计算机科学与技术系，获学士学位

1999年7月-2005年6月，清华大学计算机科学与技术专业，获工学博士学位

2005年8月-2007年8月，香港中文大学博士后研究员

2007年8月-2008年12月，清华大学深圳研究生院讲师

2008年5月至今，香港中文大学荣誉副研究员

2008年12月至今，清华大学深圳研究生院副研究员

《语音信号数字处理》

《大数据分析（B）》

研究工作主要围绕构建和谐的人机交互环境所需的语音及视觉处理技术等展开，具体的研究内容包括：智能语音交互、语音处理、表现力可视语音合成、自然语言理解与生成、音视频双模态联合建模等。

近年发表学术论文80余篇。参与撰写和翻译著作各1部。获得教育部科学技术进步奖二等奖2项。负责或参加国家自然科学基金、863、973、香港政府研究资助局基金、粤港科技合作计划、深港创新圈等多项科研项目。

• 2017年度：

• 1.Yishuang NING, Jia JIA, Zhiyong WU, Runnan LI, Yongsheng AN, Yanfeng WANG, Helen MENG, 'Multi-task Deep Learning for User Intention Understanding in Speech Interaction Systems,' [in] Proc. AAAI. San Francisco, USA, 4-9 February, 2017. (EI: 20174104242835) (CCF A)

• 2.Runnan LI, Zhiyong WU, Yishuang NING, Lifa SUN, Helen MENG, Lianhong CAI, 'Spectro-Temporal Modelling with Time-Frequency LSTM and Structured Output Layer for Voice Conversion,' [in] Proc. INTERSPEECH. Stockholm, Sweden, 20-24 August, 2017. (EI: 20175204590811)

• 3.Yuchen HUANG, Zhiyong WU, Runnan LI, Helen MENG, Lianhong CAI, 'Multi-Task Learning for Prosodic Structure Generation using BLSTM RNN with Structured Output Layer,' [in] Proc. INTERSPEECH. Stockholm, Sweden, 20-24 August, 2017. (EI: 20175204591488)

• 4.Xi MA, Zhiyong WU, Jia JIA, Mingxing XU, Helen MENG, Lianhong CAI, 'Speech Emotion Recognition with Emotion-Pair based Framework Considering Emotion Distribution Information in Dimensional Emotion Space,' [in] Proc. INTERSPEECH. Stockholm, Sweden, 20-24 August, 2017. (EI: 20175204591394)

• 5.Yishuang NING, Zhiyong WU, Runnan LI, Jia JIA, Mingxing XU, Helen MENG, Lianhong CAI, 'Learning Cross-Lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data,' [in] Proc. ICASSP. New Orleans, USA, 5-9 March, 2017. (EI: 20172903955037)

• 6.Runnan LI, Zhiyong WU, Xunying LIU, Helen MENG, Lianhong CAI, 'Multi-Task Learning of Structured Output Layer Bidirectional LSTMs for Speech Synthesis,' [in] Proc. ICASSP. New Orleans, USA, 5-9 March, 2017. (EI: 20172903955266)

• 7.Xixin WU, Shiyin KANG, Lifa SUN, Yishuang NING, Zhiyong WU, Helen MENG, 'Attention-based Recurrent Generator with Gaussian Tolerance for Statistical Parametric Speech Synthesis,' [in] Proc. ASMMC. Stockholm, Sweden, 20-24 August, 2017. (EI)

• 2016年度：

• 8.Xinyu LAN, Xu LI, Yishuang NING, Zhiyong WU, Helen MENG, Jia JIA, Lianhong CAI, 'Low Level Descriptors based DBLSTM Bottleneck Feature for Speech Driven Talking Avatar,' [in] Proc. ICASSP. Shanghai, China, 20-25 March, 2016. (EI: 20162402488482)

• 9.Quanjie YU, Peng LIU, Zhiyong WU, Shiyin KANG, Helen MENG, Lianhong CAI, 'Learning Cross-lingual Information with Multilingual BLSTM for Speech Synthesis of Low-resource Languages,' [in] Proc. ICASSP. Shanghai, China, 20-25 March, 2016. (EI: 20162402488723)

• 10.Yaodong TANG, Yuchen HUANG, Zhiyong WU, Helen MENG, Mingxing XU, Lianhong CAI, 'Question Detection from Acoustic Features using Recurrent Neural Network with Gated Recurrent Unit,' [in] Proc. ICASSP. Shanghai, China, 20-25 March, 2016. (EI: 20162402488463)

• 11.Linchuan LI, Zhiyong WU, Mingxing XU, Helen MENG, Lianhong CAI, 'Recognizing Stances in Mandarin Social Ideological Debates with Text and Acoustic Features,' [in] Proc. ICME) Seattle, USA, 11-15 July, 2016. (EI: 20164302952120)

• 12.Linchuan LI, Zhiyong WU, Mingxing XU, Helen MENG, Lianhong CAI, 'Combining CNN and BLSTM to Extract Textual and Acoustic Features for Recognizing Stances in Mandarin Ideological Debate Competition,' [in] Proc. INTERSPEECH. San Francisco, USA, 8-12 September, 2016. (EI: 20164603003717)

• 13.Yaodong TANG, Zhiyong WU, Helen MENG, Mingxing XU, Lianhong CAI, 'Analysis on Gated Recurrent Unit based Question Detection Approach,' [in] Proc. INTERSPEECH. San Francisco, USA, 8-12 September, 2016. (EI: 20164603003979)

• 14.Xu LI, Zhiyong WU, Helen MENG, Jia JIA, Xiaoyan LOU, Lianhong CAI, 'Expressive Speech Driven Talking Avatar Synthesis with DBLSTM using Limited Amount of Emotional Bimodal Data,' [in] Proc. INTERSPEECH. San Francisco, USA, 8-12 September, 2016. (EI: 20164603004232)

• 15.Xu LI, Zhiyong WU, Helen MENG, Jia JIA, Xiaoyan LOU, Lianhong CAI, 'Phoneme Embedding and its Application to Speech Driven Talking Avatar Synthesis,' [in] Proc. INTERSPEECH. San Francisco, USA, 8-12 September, 2016. (EI: 20164603004231)

• 16.Runnan LI, Zhiyong WU, Helen MENG, Lianhong CAI, 'DBLSTM-based Multi-Task Learning for Pitch Transformation in Voice Conversion,' [in] Proc. ISCSLP. Tianjin, China, 17-20 October, 2016. (EI: 20172303743441)

• 2015年度：

• 17.Zhiyong WU, Yishuang NING, Xiao ZANG, Jia JIA, Fanbo MENG, Helen MENG, Lianhong CAI, 'Generating Emphatic Speech with Hidden Markov Model for Expressive Speech Synthesis,' Multimedia Tools and Applications, vol. 74, pp. 9909-9925, DOI: 10.1007/s11042-014-2164-2, Springer, 2015. (SCI: WOS:000364019400005, EI: 20143600027913)

• 18.Zhiyong WU, Kai ZHAO, Xixin WU, Xinyu LAN, Helen MENG, 'Acoustic to Articulatory Mapping with Deep Neural Network,' Multimedia Tools and Applications, vol. 74, pp. 9889-9907, DOI: 10.1007/s11042-014-2183-z, Springer, 2015. (SCI: WOS:000364019400004, EI: 20143600014973)

• 19.Qi LYU, Zhiyong WU, Jun ZHU, 'Polyphonic Music Modelling with LSTM-RTRBM,' [in] Proc. ACM MM. Brisbane, Australia, 26-30 October, 2015. (EI: 20161602252616) (CCF A)

• 20.Qi LYU, Zhiyong WU, Jun ZHU, Helen MENG, 'Modelling High-dimensional Sequences with LSTM-RTRBM: Application to Polyphonic Music Generation,' [in] Proc. IJCAI. Buenos Aires, Argentina, 25-31 July, 2015. (EI: 20155101693661) (CCF A)

• 21.Peng LIU, Quanjie YU, Zhiyong WU, Shiyin KANG, Helen MENG, Lianhong CAI, 'A Deep Recurrent Approach for Acoustic-to-Articulatory Inversion,' [in] Proc. ICASSP. Brisbane, Australia, 19-24 April, 2015. (EI: 20154501510018)

• 22.Yishuang NING, Zhiyong WU, Jia JIA, Fanbo MENG, Helen MENG, Lianhong CAI, 'HMM-based Emphatic Speech Synthesis for Corrective Feedback in Computer-Aided Pronunciation Training,' [in] Proc. ICASSP. Brisbane, Australia, 19-24 April, 2015. (EI: 20154501509415)

• 23.Yishuang NING, Zhiyong WU, Xiaoyan LOU, Helen MENG, Jia JIA, Lianhong CAI, 'Using Tilt for Automatic Emphasis Detection with Bayesian Networks,' [in] Proc. INTERSPEECH. Dresden, Germany, 6-10 September, 2015. (EI: 20160902029674)

• 24.Xixin WU, Zhiyong WU, Yishuang NING, Jia JIA, Lianhong CAI, Helen MENG, 'Understanding Speaking Styles of Internet Speech Data with LSTM and Low-resource Training,' [in] Proc. ACII. Xian, China, 21-24 September, 2015. (EI: 20161502238729)

• 25.孟凡博, 吴志勇, 贾珈, 蔡莲红, '汉语重音的凸显度分析与合成,' 声学学报, vol. 40, no. 1, pp. 1-11, January, 2015. (EI: 20151000618075)

• 26.黄雨晨, 徐明星, 吴志勇, 蔡莲红, '表征句式语气的声学信息分布,' [in] 全国人机语音通讯学术会议. 天津, 25-27 October, 2015.

• 2014年度：

• 27.Fanbo MENG, Zhiyong WU, Jia JIA, Helen MENG, Lianhong CAI, 'Synthesizing English Emphatic Speech for Multimodal Corrective Feedback in Computer-Aided Pronunciation Training,' Multimedia Tools and Applications, vol. 73, no. 1, pp. 463-489, DOI: 10.1007/s11042-013-1601-y, Springer, 2014. (SCI: WOS:000342418700022, EI: 20143600046713)

• 28.Jia JIA, Zhiyong WU, Shen ZHANG, Helen MENG, Lianhong CAI, 'Head and Facial Gestures Synthesis using PAD Model for an Expressive Talking Avatar,' Multimedia Tools and Applications, vol. 73, no. 1, pp. 439-461, DOI: 10.1007/s11042-013-1604-8, Springer, 2014. (SCI: WOS:000342418700023, EI: 20143600046670)

• 29.Xin ZHENG, Zhiyong WU, Helen MENG, Lianhong CAI, 'Contrastive Auto-encoder for Phoneme Recognition,' [in] Proc. ICASSP. Florence, Italy, 4-9 May, 2014. (EI: 20143218037687)

• 30.Xin ZHENG, Zhiyong WU, Helen MENG, Lianhong CAI, 'Learning Dynamic Features with Neural Networks for Phoneme Recognition,' [in] Proc. ICASSP. Florence, Italy, 4-9 May, 2014. (EI: 20143218037686)

• 31.Xiao ZANG, Zhiyong WU, Helen MENG, Jia JIA, Lianhong CAI, 'Using Conditional Random Fields to Predict Focus Word Pair in Spontaneous Spoken English,' [in] Proc. INTERSPEECH. Singapore, 14-18 September, 2014. (EI: 20144600199537)

• 32.Xixin WU, Zhiyong WU, Jia JIA, Helen MENG, Lianhong CAI, 'Automatic Speech Data Clustering with Human Perception based Weighted Distance,' [in] Proc. ISCSLP. Singapore, 12-14 September, 2014. (EI: 20144900274075)

• 33.Xiao ZANG, Zhiyong WU, Yishuang NING, Helen MENG, Lianhong CAI, 'Automatic Detection of Contrastive Word Pairs using Textual and Acoustic Features,' [in] Proc. ICSP. Hangzhou, 19-23 October, 2014. (EI: 20153101078079)

• 34.王欣, 吴志勇, 蔡莲红, '语音合成中基于稳定段边界的不定长基元选取,' 软件学报, vol. 25, Supplement (2), pp. 63-69, December, 2014. (EI: 20152100877399)

• 2013年度：

• 35.孟凡博, 吴志勇, 蒙美玲, 贾珈, 蔡莲红, '基于决策树的英语焦点语音转换,' 清华大学学报(自然科学版), vol. 53, no. 7, pp. 1046-1051, 2013. (EI: 20135217144112)

• 36.Xin ZHENG, Zhiyong WU, Binbin SHEN, Helen MENG, Lianhong CAI, 'Investigation of Tandem Deep Belief Network Approach for Phoneme Recognition,' [in] Proc. ICASSP. Vancouver, Canada, 26-31 May 2013. (EI: 20135217121577)

• 37.Jianbo JIANG, Zhiyong WU, Mingxing XU, Jia JIA, Lianhong CAI, 'Comparing Feature Dimension Reduction Algorithms for GMM-SVM based Speech Emotion Recognition,' [in] Proc. APSIPA ASC. Taiwan, China, 29 October-1 November 2013. (EI: 20140717305313)

• 38.Kai ZHAO, Zhiyong WU, Lianhong CAI, 'A Real-time Speech Driven Talking Avatar based on Deep Neural Network,' [in] Proc. APSIPA ASC. Taiwan, China, 29 October-1 November 2013. (EI: 20140717305312)

• 2012年度：

• 39.Jianbo JIANG, Zhiyong WU, Mingxing XU, Jia JIA, Lianhong CAI, 'Comparison of Adaptation Methods for GMM-SVM based Speech Emotion Recognition,' [in] Proc. IEEE Workshop on SLT, pp. 269-273. Miami, Florida, USA, 2-5 December 2012. (EI: 20130916065166)

• 40.Tao JIANG, Zhiyong WU, Jia JIA, Lianhong CAI, 'Perceptual Clustering based Unit Selection Optimization for Concatenative Text-to-Speech Synthesis,' [in] Proc. ISCSLP, pp. 64-68. Hong Kong, 5-8 December 2012. (EI: 20131016084519)

• 41.Chunrong LI, Zhiyong WU, Fanbo MENG, Helen MENG, Lianhong CAI, 'Detection and Emphatic Realization of Contrastive Word Pairs for Expressive Text-to-Speech Synthesis,' [in] Proc. ISCSLP, pp. 93-97. Hong Kong, 5-8 December 2012. (EI: 20131016084523)

• 42.Xixin WU, Zhiyong WU, Jia JIA, Lianhong CAI, 'Adaptive Named Entity Recognition based on Conditional Random Fields with Automatic Updated Dynamic Gazetteers,' [in] Proc. ISCSLP, pp. 363-367. Hong Kong, 5-8 December 2012. (EI: 20131016084525)

• 43.Jia JIA, Xiaohui WANG, Zhiyong WU, Lianhong CAI, Helen MENG, 'Modeling the Correlation between Modality Semantics and Facial Expressions,' [in] Proc. APSIPA ASC. Hollywood, USA, 3-6 December 2012. (EI: 20131016079234)

• 44.Fanbo MENG, Zhiyong WU, Helen MENG, Jia JIA, Lianhong CAI, 'Hierarchical English Emphatic Speech Synthesis based on HMM with Limited Training Data,' [in] Proc. INTERSPEECH. Portland, USA, 8-13 September 2012. (EI: 20132316399086)

• 45.Fanbo MENG, Zhiyong WU, Helen MENG, Jia JIA, Lianhong CAI, 'Generating Emphasis from Neutral Speech using Hierarchical Perturbation Model by Decision Tree and Support Vector Machine,' [in] Proc. ICALIP, pp. 442-448. Shanghai, China, 16-18 July 2012. (EI: 20130315907216)

• 46.Kai ZHAO, Zhiyong WU, Jia JIA, Lianhong CAI, 'An Online Speech Driven Talking Head System,' [in] Proc. GHTCE, pp. 186-187. Shenzhen, China, 18-20 November 2012. (EI: 20131716244276)

• 47.Xin WANG, Zhiyong WU, 'An HMM-based Cantonese Speech Synthesis System,' [in] Proc. GHTCE, pp. 141-142. Shenzhen, China, 18-20 November 2012. (EI: 20131716244264)

• 48.Zhang ZHANG, Zhiyong WU, Jia JIA, Lianhong CAI, 'Modeling Prosody Pattern of Chinese Expressive Speech and Its Application in Personalized Speech Conversion,' [in] Proc. TAL, Nanjing, China, 26-29 May 2012.

• 49.姜涛, 吴志勇, 蔡莲红, '语音合成自然度的客观度量实验研究,' [in] 第十届中国语音学学术会议(PCC). 上海, 18-20 May 2012.

• 2011年度：

• 50.Binbin SHEN, Zhiyong WU, Yongxin WANG, Lianhong CAI, 'Combining Active and Semi-supervised Learning for Homograph Disambiguation in Mandarin Text-to-Speech Synthesis,' [in] Proc. INTERSPEECH. Florence, Italy, 27-31 August, 2011. (EI: 20123715411045)

• 51. Hui PANG, Zhiyong WU, Lianhong CAI, 'Modeling Pitch Contour of Chinese Mandarin Sentences with the PENTA Model,' [in] Proc. NCMMSC. Xi'an, 16-18 October, 2011. Also published in Tsinghua Science and Technology (清华大学学报英文版), 2012, 17(2): 218-224. (EI: 20123215322698) (Best Paper Award/优秀论文)

• 52.陈龙, 吴志勇, 袁春, 蒙美玲, 蔡莲红, '面向数字版权管理的声纹辅助认证系统,' [in] Proc. NCMMSC. Xi'an, 16-18 October, 2011.

• 2010年度：

• 53.Zhiyong WU, Lianhong CAI, Helen MENG, 'Modeling Prosody Patterns for Chinese Expressive Text-to-Speech Synthesis,' [in] Proc. ISCSLP. Tainan, 29 November-3 December 2010. (EI: 20110713663203)

• 54.Fanbo MENG, Helen MENG, Zhiyong WU, Lianhong CAI, 'Synthesizing Expressive Speech to Convey Focus using a Perturbation Model for Computer-Aided Pronunciation Training,' [in] Proc. L2WS. Tokyo, Japan, 22-27 September 2010.

• 55.Quansheng DUAN, Shiyin KANG, Zhiyong WU, Lianhong CAI, Zhiwei SHUANG, Yong QIN, 'Comparison of Syllable/Phone HMM Based Mandarin TTS,' [in] Proc. ICPR, pp. 4496-4499. Istanbul, Turkey, 23-26 August 2010. (ISTP: 11580140, EI: 20104613390878)

• 56.Shen ZHANG, Zhiyong WU, Helen MENG, Lianhong CAI, 'Facial expression synthesis based on emotion dimensions for affective talking avatar,' T. Nishida et al. (Eds.): Modeling Machine Emotions for Realizing Intelligence, SIST (Smart Innovation, Systems and Technologies), vol. 2010, no. 1, pp. 109-132, 2010. (EI: 20123715421851)

• 57.张章, 贾珈, 蔡莲红, 吴志勇, '汉语音高模式及参数化描述的研究,' [in] 第九届中国语音学学术会议(PCC). 天津, 28-30 May 2010.

• 2009年度：

• 58.Zhiyong WU, Helen MENG, Hongwu YANG, Lianhong CAI, 'Modeling the Expressivity of Input Text Semantics for Chinese Text-to-Speech Synthesis in a Spoken Dialog System,' IEEE Transaction on Audio, Speech and Language Processing, vol. 17, no. 8, pp. 1567-1577, November, 2009. (SCI: 482QK, EI: 20093612281690)

• 59. Zhiyong WU, Quanqqi CAO, Helen M. MENG, Lianhong CAI, 'A Unified Framework for Multilingual Text-to-Speech Synthesis with SSML Specification as Interface,' [in] Proc. NCMMSC2009. Urumqi, Xinjiang, 14-16 August, 2009. Also published in Tsinghua Science and Technology (清华大学学报英文版), vol. 14, no. 5, pp. 623-630, October 2009. (EI: 20094012358727)

• 60.段全盛, 康世胤, 双志伟, 吴志勇, 蔡莲红, 秦勇, '一种适合HMM汉语语音合成的建模单元挑选算法,' [in] 第十届全国人机语音通讯学术会议 (NCMMSC2009), 434-439. 甘肃, 兰州, 2009.8.14-16.

• 2008年度：

• 61.Zhiyong WU, Jiying WU, Helen M. MENG, 'The Use of Dynamic Deformable Templates for Lip Tracking in an Audio-Visual Corpus with Large Variations in Head Pose, Face Illumination and Lip Shapes,' [in] Proc. ISCSLP 2008. Kunming, China, 16-19 December 2008. (EI: 20091011939107)

• 62.Honglei CONG, Zhiyong WU, Lianhong CAI, Helen M. MENG, 'A New Prosodic Strength Calculation Method for Prosody Reduction Modeling,' [in] Proc. ISCSLP. Kunming, China, 16-19 December 2008. (EI: 20091011939031)

• 63.Xinxin ZHOU, Zhiyong WU, Chun YUAN, Yuzhuo ZHONG, 'Document Structure Analysis and Text Normalization for Chinese Putonghua and Cantonese Text-to-Speech Synthesis,' [in] Proc. IITA. Shanghai, China, 20-22 December 2008. (EI: 20091411996990)

• 64.Yu WANG, Zhiyong WU, Lianhong CAI, Helen M. MENG, 'Modeling the Synchrony between Audio and Visual Modalities for Speaker Identification,' [in] Proc. PCC. Beijing, China, 18-20 April 2008.

• 2007年度：

• 65.Shen ZHANG, Zhiyong WU, Helen M. MENG, Lianhong CAI, 'Facial Expression Synthesis Using PAD Emotional Parameters for a Chinese Expressive Avatar,' [in] Proc. ACII2007, LNCS 4738, pp. 24-35. Lisbon, Portugal, 12-14 September 2007. (EI: 080311024879)

• 66.Shen ZHANG, Zhiyong WU, Helen M. MENG, Lianhong CAI, 'Head Movement Synthesis based on Semantic and Prosodic Features for a Chinese Expressive Avatar,' [in] Proc. ICASSP. Honolulu, Hawaii, USA, April 15-20 2007. (EI: 073210745929)

• 67.Hongwu YANG, Helen M. MENG, Zhiyong WU, Lianhong CAI, 'Modelling the Global Acoustic Correlates of Expressivity for Chinese Text-to-speech Synthesis,' [in] IEEE/ACL SLT. Aruba, 10-13 December 2006. (EI: 083311451167)

• 2006年度：

• 68.Zhiyong WU, Lianhong CAI, Helen MENG, 'Weight Estimation for Audio-Visual Multi-level Fusion in Bimodal Speaker Identification,' [in] D. Huang, K. Li and G.W. Irwin (Eds.): Intelligent Computing in Signal Processing and Pattern Recognition (ICIC2006), LNCIS 345, pp. 1107-1112. Kunming, China, 16-19 August 2006. (SCI: BEZ63, ISTP: BEZ63)

• 69.Zhiyong WU, Lianhong CAI, Helen MENG, 'Multi-level Fusion of Audio and Visual Features for Speaker Identification,' [in] D. Zhang and A.K. Jain (Eds.): Advances in Biometrics (ICB2006), LNCS 3832, pp. 493-499, 2005. Hong Kong, 5-7 January 2006. (SCI: BDW04, ISTP: BDW04, EI: 06249940530)

• 70.Zhiyong WU, Helen M. MENG, Hui NING, Sam C. TSE, 'A Corpus-based Approach for Cooperative Response Generation in a Dialog System,' [in] Qiang Huo, Bin Ma, Eng-Siong Chng and Haizhou Li (Eds.): Chinese Spoken Language Processing (ISCSLP2006), LNAI 4274, pp. 614-626. Kent Ridge, Singapore, 13-16 December 2006. (ISTP: BFV54, EI: 20100912736133)

• 71.Zhiyong WU, Shen ZHANG, Lianhong CAI, Helen MENG, 'Real-time Synthesis of Chinese Visual Speech and Facial Expressions using MPEG-4 FAP Features in a Three-dimensional Avatar,' [in] Proc. International Conference on Spoken Language Processing (INTERSPEECH, ICSLP), pp. 1802-1805. Pittsburgh, USA, 17-21 September 2006. (EI: 082511324456)

• 72.吴志勇, 蔡莲红, 马磊, 贾珈, '多生物特征识别平台的设计与实现,' 小型微型计算机系统, 2006: 27(2), 375-379.

• 73.吴志勇, 蔡莲红, '基于动态贝叶斯网络的音视频双模态说话人识别,' 计算机研究与发展, 2006: 43(3), 470-475.

• 2005年度及之前：

• 74.吴志勇, 蔡莲红, 蔡锐, '语音合成中基于听辨指导的权重训练算法,' 清华大学学报(自然科学版), 2005: 45(1), 52-56.

• 75.吴志勇, 蔡莲红, 蒙美玲, '可视语音合成中基于音视频关联模型的视位参数优化,' [In] 第六届全国人机语音通讯学术会议(NCMMSC2005), 334-337. 北京, 2005.10.22-24. (Best Paper Award/优秀论文)

• 76.吴志勇, 蔡莲红, '语音合成中的韵律关联模型,' 中文信息学报, 2004: 18(2), 44-50.

• 77.王志明, 蔡莲红, 吴志勇, 陶建华, '汉语文本-可视语音转换的研究,' 小型微型计算机系统, 2002: 23(4), 474-477.