基本信息

陶建华 男 研究员 博士生导师

中国科学院自动化研究所
模式识别国家重点实验室 副主任

中欧信息自动化应用数学联合实验室 中方主任


国家杰出青年科学基金获得者

国家“万人计划”领军人才

邮件:jhtao@nlpr.ia.ac.cn
电话:010-82544599
地址:北京市中关村东路95号中科院自动化所
邮编:100190

研究领域

语音识别与合成、人机交互、模式识别、网络音视频信息处理

教育背景

   
学历
清华大学计算机系     1998年3月--2001年6月 获博士学位
南京大学电子系 1993年9月--1996年6月 获硕士学位
南京大学信息物理系  1989年9月--1993年6月 获本科学位

工作经历

工作简历
2003年至今,中国科学院自动化研究所模式识别国家重点实验室工作,现为实验室副主任
 
期刊任职
IEEE Transactions on Affective Computing,Steering Committee Member

Speech Communication,Subject Editor

International Journal on Multimodal User Interface, Editorial Board Member

International Journal on Synthetic Emotions,Editorial Board Member

声学学报,编委

信号处理学报,编委

学会任职

AAAC Association,Executive Committee Member

中国计算机学会,会士、常务理事

中国人工智能学会,理事

中国中文信息学会,理事(兼语音信息处理专业委员会副主任)

中国图形图像学会,理事(兼人机交互专业委员会主任)

中国声学学会,理事

中国语言学会语音学分会,副主任

中文语言资源联盟,秘书长


专利与奖励

荣誉
(1)2014年获国家杰出青年科学基金支持
(2) 2002年、2014年北京市科技进步二等奖
(3) Eurospeech2001语音平台竞赛优胜者
(4) 2013年、2014年、2016年、2017年全国人机交互学术会议优秀论文或提名
(5) 2005年全国信号处理会议优秀论文  
(6) 2001 年、2015年、2017年全国人机语音会议优秀论文

发明专利

(1) 基于音节韵律约束关系的汉语语音合成方法及系统,专利号:200610076015.1
(2) 基于组块分析的韵律短语预测方法,专利号:200610073102.1
(3) 一种嵌入式语音合成方法及系统,专利号:200510086311.5
(4) 基于语音转换的情感语音生成方法,专利号:200610076014.7
(5) 基于隐马尔可夫模型状态映射的文本无关语音转换系统,专利号:200910089586.2
(6) 基于正交图像的快速个性化人脸建模方法,专利号:200510108136.5
(7) 基于逆滤波的谐波噪声激励模型声码器,专利号:201110140269.6
(8) 一种对普通话重音进行层次化建模和预测的方法,专利号:201110200330.1
(9) 发音器官可视语音合成系统,专利号:201210265448.7
(10) 语音合成中时长参数的生成方法,专利号:201110160419.X
(11) 基于残差信号频谱重构的声码器,专利号:201210253946.X
(12) 在医学影像中获取发音器官轮廓的方法,专利号:201210272187.1
(13) 音频数据的编码方法及解码方法,专利号:201210487489.0
(14) 一种波形拼接语音合成的选音方法,专利号:201310481306.9
(15) 一种语音数据的编码及解码方法,专利号:201310176701.6
(16) 一种融合长跨度情感历史的语音情感识别方法,专利号:201310481318.1
(17) 一种高效的语音检测方法,专利号:201310743203.5
(18) 发音器官的网格动画生成方法,专利号:201310746136.2
(18) 一种基于边缘特征的道路检测方法,专利号:201310597554.X            
(20) 一种基于邮件截获的电力敏感信息检测方法,专利号:201010539807.4

出版信息

发表论文 

1)      Ya Li,Jianhua Tao,Wei Lai,Xiaoying Xu, "Quantitative intonation modeling of interrogative sentences for Mandarin speech synthesis" Speech Communication,Volume 89, PP:92-102,2017.05,.

2)      Zhengqi Wen,Kehuang Li,Zhen Huang,Chin-Hui Lee,Jianhua Tao, "Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning" Journal of Signal Processing Systems,2017.10.02,DOI 10.1007/s11265-017-1293-z..

3)      Yibin Zheng,Ya Li,Zhengqi Wen,Bin Liu and Jianhua Tao, "Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin" IEEE Journal of Signal Processing System,2017.9.26,DOI 10.1007/s11265-017-1290-2,.

4)      Jiangyan Yi,Zhengqi Wen,Jianhua Tao,Hao Ni,Bin Liu, "CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition" Journal of Signal Processing Systems,2017.9.23,DOI 10.1007/s11265-017-1291-1,.

5)      Bin Liu,Jianhua Tao,Dawei Zhang,Yibin Zheng, "A Novel Pitch Extraction Based On Jointly Trained Deep BLSTM Recurrent Neural Networks With Bottleneck Features" ICASSP 2017,PP:336-340,March.5-9,2017,New Orleans,

6)      Jiangyan Yi,Jianghua Tao,Zhengqi Wen and Ya Li, "Distilling Knowledge from an Ensemble of Models for Punctuation Prediction" 18th Annual Conference of the Speech Communication Associatio(Interspeech 2017), PP:2779-2783,August 20-24, 2017, Sweden,Stockholm,

7)      Jian Huang,Ya Li, Jianhua Tao, Jiangyan YI, "Effect of Dimensional Emotion in Discrete Speech Emotion Classification" 2017 Affective Social Multimedia Computing( ASMMC 2017), Stockholm Sweden.

8)      Jian Huang,Ya Li,Jianhua Tao,Zhen Lian, Zhengqi wen, Minghao Ynag,Jiangyan YI, "Continuous Multimodal Emotion Prediction Based on Long Short Term Memory Recurrent Neural Network" The Audio/Visual Emotion Challenge and Workshop (AVEC 2017), PP:11-18,October 23,2017,Mountain View,CA,USA.

9)      Bocheng Zhao,Minghao Yang,Hang Pan,Qingjie Zhu,Jianghua Tao, "Nonrigid Point Matching of Chinese Characters for Robot Writing" IEEE Ro,PP:762-767, 2017.8.25,Macao,China,

10)   Xiaoke Qi,JianhuaTao, "A Domain Knowledge-Assisted Nonlinear Model for Head-Related Transfer Functions Based on Bottleneck Deep Neural Network" 18th Annual Conference of the Speech Communication Associatio(Interspeech 2017),PP:3058-3062, Agu 21,2017,Stockholm, Sweden,

11)   Yibin Zheng,Jianhua Tao,Zhengqi Wen,Ya Li and Bin Liu, "Investigating Efficient Feature Representation Method and Training Object Function for BLSTM-based Phone Duration Prediction" 18th Annual Conference of the Speech Communication Associatio(Interspeech 2017), PP:784-788, Agu 21,2017, Stockholm,Sweden,

12)   刘斌,陶建华, "联合长短时记忆递归神经网络和非负矩阵分解的语音混响消除方法" 信号处理,Vol.33,No.3,pp.268-272,2017.03.

13)   Xiaoke Qi,JianhuaTao, "Distance-Dependent Modeling of Head-Related Transfer Functions Based on Spherical Fourier-Bessel Transform" 第十四届全国人机语音通讯学术会议, 2017.10.11-13,江苏,连云港.

14)   Jiangyan Yi,Jianhua Tao,Zhengqi Wen,Ya Li and Hao Ni, "Acoustic Model Compression with Knowledge Transfer" 第十四届中国语音学学术会议, 2017.10. 11-13, 江苏,连云港.

15)   傅睿博,李雅,温正棋,陶建华, "基于静音时长和文本特征融合的韵律边界自动标注" 第十四届中国语音学学术会议,2017.10.11-13,江苏,连云港,最佳学生论文奖.

16)   杨明浩,张珂,赵博程,朱庆杰,潘航,那燊若阳,湛永松,陶建华, "具有智能交互学习能力的机械臂写字系统" 第十三届全国人机交互学术会议,2017.07. 24-26,青岛,山东,最佳论文奖.

17)   张大伟,杨明浩,陶建华, "基于医学影像的语音驱动舌位运动合成" 第十四届全国人机语音通讯学术会议,PP:157-162,2017.10.11-13,江苏,连云港.

18)   易江燕,陶建华,刘斌,温正棋, "基于迁移学习的鲁棒语音识别声学建模方法" 第十四届中国语音学学术会议,2017.10.11-13,江苏,连云港.

19)   潘航,杨明浩,朱庆杰,湛永松,陶建华, "面向人机交互的准确人手检测方法" 第十三届全国人机交互学术会议,2017.07. 24-26,青岛,山东.

20)   周惠,杨明浩,潘航,唐仁俊,那燊若阳,湛永松,陶建华, "面向手势跟踪的卷积神经网络结构与参数分析" 第十三届全国人机交互学术会议,2017.07. 24-26,青岛,山东.

21)   郑艺斌,陶建华,李雅,温正棋,刘斌, "基于注意力的端到端韵律结构和重音联合预测方法" 第十四届全国人机语音通讯学术会议,2017.10.11-13,江苏,连云港.

22)   乌日其其格,陶建华,白音门德,易江燕,温正棋,白烨, "面向语音识别的蒙古语标准音语音库的建立" 第十六届全国少数民族语言文字信息处理学术研讨会, 2017.09.21-22,广西,桂林.

23)   Minghao Yang,Jinlin Jiang,Jianhua Tao,Kaihui Mu,Hao Li, "Emotional head motion predicting from prosodic and linguistic features" Multimedia Tools and Applications,2016,75(9):5125-5146..

24)   Ya Li*, Jianhua Tao, Linlin Chao,Wei Bao, Yazhu Liu, "CHEAVD: a Chinese natural emotional audio–visual database" Journal of Ambient Intelligence and Humanized Computing,DOI: 10.1007/s12652-016-0406-z..

25)   Bin Liu,Jianhua Tao,Zhengqi Wen,Fuyuan Mo, "Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement" Signal Processing Systems,2016, 82(2):141-150,.

26)   Hao Che,Ya Li,Jianhua Tao,Zhengqi Wen, "Investigating Effect of Rich Syntactic Features on Mandarin Prosodic Phrase Boundaries Prediction" Journal of Signal Processing Systems,2016, 82(2):263-271,.

27)   Dawei Zhang, Minghao Yang, Jianhua Tao, Yang Wang, Bin Liu, Danish Bukhari, "Extraction of Tongue Contour in Real-time Magnetic Resonance Imaging Sequences" 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016),PP:937-941,Mar.20-25,2016,Shanghai, China,

28)   Linlin Chao,Jianhua Tao,Minghao Yang,Ya Li,Zhengqi Wen, "Long short term memory recurrent neural network based encoding method for emotion recognition in video" 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016),PP:2752-2756,Mar.20-25,2016,Shanghai, China,

29)   Bin Liu,Jianhua Tao, "A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-based Sparse Representation" 17th Annual Conference of the Speech Communication Associatio(Interspeech 2016),PP:3778-3782,Sept.8-12,2016,San Francisco,USA,

30)   Yibin Zheng,Ya Li,Zhengqi Wen, Xingguang Ding, Jianhua Tao, "Improving Prosodic Boundaries Prediction for Mandarin Speech Synthesis by Using Enhanced Embedding Feature and Model Fusion Approaches" 17th Annual Conference of the Speech Communication Associatio(Interspeech 2016),PP:3201-3205, Sep 8-12, 2016,San Francisco,USA,

31)   Xiaoke Qi, Jianhua Tao, "A Sparse Spherical Harmonic-Based Model in Subbands for Head-Related Transfer Functions" 17th Annual Conference of the Speech Communication Associatio(Interspeech 2016),PP:540-544,Sept.8-12,2016,San Francisco,USA,

32)   Zhengqi Wen, Ya Li and Jianhua Tao, "The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis" 17th Annual Conference of the Speech Communication Associatio(Interspeech 2016),PP:2248-2252,Sep 8-12, 2016,San Francisco,USA,

33)   Yibin Zheng,Zhengqi Wen,Bin Liu, Ya Li, Jianhua Tao, "An Initial Research: Towards Accurate Pitch Extraction for Speech Synthesis Based on BLSTM" 13th International Conference on Signal Processing ICSP2016,PP165-170,Nov 6-10,2016,Chengdou,China,

34)   Yibin Zheng,Ya Li,Zhengqi Wen, Bin Liu, Jianhua Tao, "Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin" 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016),Oct 17-20,2016,Tianjin,China,

35)   Yibin Zheng,Ya Li,Zhengqi Wen, Bin Liu, Jianhua Tao, "Text-based sentential stress prediction using continuous lexical embedding for Mandarin speech synthesis" 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016),Oct 17-20,2016,Tianjin,China,

36)   Jiangyan Yi, Hao Ni, Zhengqi Wen, Bin Liu, Jianhua Tao, "CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition" 10th International Symposium on Chinese Spoken Language ProcessingISCSLP 2016),Oct 17-20,2016,Tianjin,China,

37)   Ye Bai,Jiangyan Yi,Hao Ni,Zhengqi Wen,Bin Liu,Ya Li,Jianhua Tao, "End-to-end Keywords Spotting Based on Connectionist Temporal Classification for Mandarin" 10th International Symposium on Chinese Spoken Language ProcessingISCSLP 2016),Oct 17-20,2016,Tianjin,China,

38)   Hao Ni, Jiangyan Yi, Zhengqi Wen, Bin Liu, Jianhua Tao, "Improving Accented Mandarin Speech Recognition by Using Recurrent Neural Network based Language Model Adaptation" 10th International Symposium on Chinese Spoken Language ProcessingISCSLP 2016),Oct 17-20,2016,Tianjin,China,

39)   Zhengqi Wen,Kehuang Li, Zhen Huang, Jianhua Tao and Chin-Hui Lee, "Learning Auxiliary Categorization for Neural Network Based Speech Synthesis" 10th International Symposium on Chinese Spoken Language ProcessingISCSLP 2016),Oct 17-20,2016,Tianjin,China,

40)   Jiangyan Yi, Hao Ni, Zhengqi Wen, Jianhua Tao, "Improving BLSTM RNN Based Mandarin Speech Recognition Using Accent Dependent Bottleneck Features" 8th Asia-Pacific Signal and Information Processing Association(APSIPA 2016),Dec 12-16,2016,Jeju, Korea,

41)   Zhengqi Wen,Kehuang Li, Jianhua Tao and Chin-Hui Lee, "DEEP NEURAL NETWORK FOR VOICE CONVERSION WITH A SYNTHESIZED PARALLEL CORPUS" 8th Asia-Pacific Signal and Information Processing Association(APSIPA 2016),Dec 12-16,2016,Jeju, Korea,

42)   Renjun Tang,Ke Zhang,Ruoyang Nashen,Minghao Yang,Hui Zhou,Qingjie Zhu,Yongsong Zhan,Jianhua Tao, "Football News Generation from Chinese Live Webcast Script" The Fifth Conference on Natural Language Processing and Chinese Computing & The Twenty Fourth International Conference on Computer Processing of Oriental Languages(NLPCC-ICCPCOL 2016),Dec 2-6,2016,Kunming, China,

43)   Jianhua Tao, Yibin Zheng,Zhengqi Wen, Ya Li, Bin Liu, "A BLSTM Guided Unit Selection Synthesis System for Blizzard Challenge 2016" Blizzard Challenge 2016,Sep 16,2016,San Francisco,USA.

44)   李雅,陶建华, Bj?rn Schuller, 山世光,蒋冬梅,贾珈, "MEC 2016: The multimodal emotion recognition challenge of CCPR 2016" 全国模式识别学术会议(7th Chinese Conference, CCPR 2016),PP.667–6782016115-7,成都,

45)   倪浩,易江燕,温正棋,陶建华 , "Recurrent Neural Network based Language Model Adaptation for Accent Mandarin Speech" 全国模式识别学术会议(7th Chinese Conference, CCPR 2016),PP:607-617,2016115-7,成都,

46)   张珂,杨明浩,湛永松, 那燊若阳,高庭丽,张大伟,朱庆杰,陶建华, "自我对话:一种面向用户教授意图的答案反馈方法" 2016全国人机交互学术会议(CHCI2016,2016826-28,上海.

47)   那燊若阳,杨明浩,张满囤,刘阔,陶建华, "Task Oriented Human Robot Interaction from User’s Vague Instructions" 2016全国人机交互学术会议(CHCI2016,2016826-28,上海.

48)   Keikichi HiroseJianhua Tao, "Speech Prosody in Speech SynthesisModeling and generation of prosody for high quality and flexible speech synthesis" Springer,ISBN 978-3-662-45257-8,March 2015.

49)   Ya LiJianhua Tao , "Mandarin Stress Analysis and Prediction for Speech Synthesis " Springer,PP83-95.March 2015.

50)   Nick CampbellYa Li, , "Expressivity in Interactive Speech Synthesis; Some Paralinguistic and Nonlinguistic Issues of Speech Prosody for Conversational Dialogue Systems" Springer,PP96-107,March 2015.

51)   Minghao Yang,Jianhua Tao,Linlin Chao,Hao Li,Dawei Zhang,Hao Che,Tingli Gao,Bin Liu, "User behavior fusion in dialog management with multi-modal history cues" Multimedia Tools and Applications,Volume 74, Issue 22 (2015), Page 10025-10051,.

52)   Ya Li,Jianhua Tao,Hirose,K.,Xiaoying Xu,Wei Lai , "Hierarchical stress modeling and generation in mandarin for expressive Text-to-Speech" Speech Communication,Vol.72,pp.59-73,.

53)   Wang Xiaoyan,Yang Minghao,Xia Ming,Zhan Yongsong,Shi LihuiMa,Chuanyan Tao,Jianhua,Chen Shengyong, "Fast unsupervised texture segmentation using Texel similarity map" Journal Of Modern Optics,2015Volume: 62 Issue: 15 Page: 1211-1222,.

54)   Su-Jing Wang,Wen-Jing Yan,Xiaobai Li,Guoying Zhao,Chun-Guang Zhou,Xiaolan Fu,Minghao Yang,Jianhua Ta, "Micro-Expression Recognition Using Color Spaces" IEEE Transactions on Image Processing,Vol. 24, No. 12, PP:6034-6047,December 2015,.

55)   Bin Liu,Jianhua Tao,Zhengqi Wen,Ya Li,Danish Bukhari, "A Novel Method of Artificial Bandwidth Extension Using Deep Architecture" 16th Annual Conference of the Speech Communication Associatio(Interspeech 2015),PP:2598-2602,Sept.6-10,2015,Dresden,Germany,

56)   Hao Li,Jianhua Tao,Minghao Yang,Bin Liu, "Estimate Articulatory MRI Series From Acoustic Signal Using Deep Architecture " 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2015),PP:4854-4858,Apr.19-24,2015,Brisbane,Australia,

57)   Hao Li,Jianhua Tao,Yang Wang, "Evaluation of Linear Regression for Speaker Adaptation in HMM-Based Articulatory Movements Estimation" 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2015),PP:4944-4948,Apr.19-24,2015,Brisbane,Australia;,

58)   Linlin Chao,Jianhua Tao,Minghao Yang,Ya Li, "Multi Task Sequence Learning for Depression Scale Prediction from Video" 6th Affecive Computing and Intelligent Interaction(ACII 2015),PP:525-531,Sep.21-24,2015,Xian,China,

59)   Ya Li,Yazhu Liu,Wei Bao, Linlin Chao,Jianhua Tao, "From Simulated Speech to Natural Speech, What are the Robust Features for Emotion Recognition?" 6th Affecive Computing and Intelligent Interaction(ACII 2015),PP:368-373,Sep.21-24,2015,Xian,China,

60)   Ya Li,Nick Campbell,Jianhua Tao, "VOICE QUALITY: NOT ONLY ABOUT “YOU” BUT ALSO ABOUT “YOUR INTERLOCUTOR”" 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2015),PP:4739-4743,Apr.19-24,2015,Brisbane,Australia; ,

61)   Yang Wang,Minghao Yang,Zhengqi Wen,Jianhua Tao, "Combining Extreme Learning Machine and Decision Tree for Duration Prediction in HMM based Speech Synthesis" 16th Annual Conference of the Speech Communication Associatio(Interspeech 2015),PP:2197-2201,Sept.6-10,2015,Dresden,Germany,EI ,.

62)   Linlin Chao,Jianhua Tao,Minghao Yang,Ya Li,Zhengqi Wen, "Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition" Audio/Visual Emotion Challenge (AVEC2015),PP:65-72,Oct.26,2015,Brisbane,Australia,

63)   方硕,温正棋,陶建华, "基于统计参数语音合成的疑问语气生成方法" ICPS 2015,Aug.12-19,2015.

64)   杨明浩,高廷丽,陶建华,张大伟,孙梦伊,李昊,巢林林, "人机对话中的意图及语音识别错误对交互体验的影响分析" 第十一届全国人机交互学术会议(HHME 2015),最佳论文提名奖,2015.09.11-13,辽宁.

65)   高廷丽,陶建华,杨明浩,张大伟,孙梦伊, "基于词向量模型的对话短文本意图分类方法" 第十一届全国人机交互学术会议(HHME 2015),2015.09.11-13,辽宁.

66)   鲍薇,李雅,顾明亮,陶建华,王仁宇,邱远航, "基于特征融合的汉语疑问句语气识别" 第十一届全国人机交互学术会议(HHME 2015),2015.09.11-13,辽宁.

67)   刘斌,陶建华,莫福源, "一种改进的基于分析合成框架的语音增强算法" 全国人机语音通讯学术会议(NCMMSC2015),2015.10.25-27,天津,NCMMSC2015最佳学生论文奖,

68)   方硕,温正棋,王洋,陶建华, "基于自适应训练的疑问句语音合成" 全国人机语音通讯学术会议(NCMMSC2015) ,2015.10.25-27,天津,

69)   丁星光,李雅,赖伟,陶建华, "基于深度学习的韵律结构预测" 全国人机语音通讯学术会议(NCMMSC2015) ,2015.10.25-27,天津,

70)   赖玮,李雅,许小颖,丁星光,陶建华, "汉语无标记疑问句的语调分析与建模" 全国人机语音通讯学术会议(NCMMSC2015) ,2015.10.25-27,天津,

71)   鲍薇,李雅,MagdalenaOleskowicz-Popiel,顾明亮,陶建华, "面向多语言的情感语音感知研究" 全国人机语音通讯学术会议(NCMMSC2015) ,2015.10.25-27,天津,

72)   Zhengqi Wen,Jianhua Tao,Shifeng Pan,Yang Wang, "Pitch-Scaled Spectrum Based Excitation Model for HMM-based Speech Synthesis" Journal of Signal Processing SystemsMarch 2014,Volume 74,Issue 3,PP423-435.

73)   Ya Li, Jianhua Tao, Keikichi Hirose,Wei Lai,Xiaoying Xu, "Hierarchical stress generation with Fujisaki model in expressive speech synthesis" SPEECH PROSODY 2014,May 20-23,PP:1032-1036,Dublin Ireland.

74)   Shanfeng Liu, Zhengqi Wen, Jianhua Tao, Ya Li, Yongguo Kang, "A Data Driven Method for Target and Concatenation Cost Calculation with KL-Divergence in Mandarin Hybrid Speech Synthesis" The 12th IEEE International Conference on Signal ProcessingPP:572-576,Oct 19-23,2014HangZhou, China

75)   Hao che, Jianhua Tao, Ya LiZhengqi Wen, "Investigating Effect of Rich Syntactic Features on Mandarin Prosodic Phrase Boundaries Prediction" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),PP:501-505,Sept 12-14Singapore

76)   Ran Zhang , Zhengqi Wen , Jianhua Tao , Ya Li , Bing Liu, Xiaoyan Lou, "A Hierarchical Viterbi Algorithm for Mandarin Hybrid Speech Synthesis System" 2014 InterspeechPP:795-799Sept 14-18Singapore

77)   Hao Che, Jianhua Tao, Ya Li, "Improving Mandarin Prosodic Boundary Prediction with Rich Syntactic Features" 2014 InterspeechPP:46-50Sept 14-19Singapore

78)   Bin Liu, Jianhua Tao, Fuyuan Mo, Ya Li, Zhengqi Wen, Shanfeng Liu, "Efficient Voice Activity Detection Algorithm based on Sub-band Temporal Envelope and Sub-band Long-term Signal Variability" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),pp.531-535,Sep 12-14, 2014Singapore

79)   Linlin Chao, Jianhua Tao, Minghao Yang, Ya Li, "Improving Generation Performance of Speech Emotion Recognition by Denoising Autoencoders" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),PP:341-344,Sept12-14,2014Singapore

80)   Linlin Chao,Jianhua Tao,Minghao Yang,Ya li,Zhengqi Wen, "Multi-scale Temporal Modeling by Neural Networks for Dimensional Emotion Recognition in Video" AVEC ACM Multimedia 2014PP:11-18Nov 2-7NY, USA

81)   Shanfeng Liu, Zhengqi Wen, Ya Li, Jianhua Tao, Bin Liu, "Context Features Based Pre-Selection and Weight Prediction in Concatenation Speech Synthesis System" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),PP:506-510,Sept12-14,2014Singapore

82)   Bin Liu, Fuyuan Mo, Jianhua Tao, "Speech enhancement based on analysis-synthesis framework with improved pitch estimation and spectral envelope enhancement" 2014 International Conference on Signal ProcessingICSP 2014),pp.461-467,Oct 19-23, Hangzhou, China

83)   Yang Wang, Jianhua Tao, "Evaluation of Parameter Generation Using High Order Dynamic Features and Long Span Windows for HMM based Speech Synthesis" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),pp.516-520,Sep 12-14, 2014Singapore

84)   Xiaoying Xu,Huimin Wang,Ya Li,Wei Lai,Jianhua Tao, "The Expression Of Emotions by Text and Speech" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),Sep 12-14, 2014Singapore

85)   Hao Li, Minghao Yang, Jianhua Tao, "TONGUE SHAPE CONVERSION WITH NON-PARALLEL TRAINING DATA" 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (2014 ICASSP)PP: 2569-2572,May 4-9,2015,Florence,Italy

86)   Ran Zhang,Jianhua Tao,Ya Li,Zhengqi Wen, "A NOVEL HYBRID MANDARIN SPEECH SYNTHESIS SYSTEM USING DIFFERENT BASE UNITS FOR MODEL TRAINING AND CONCATENATION" 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (2014 ICASSP),May 4-9,2014,PP: 295-299,Florence,Italy.

87)   Wei Bao,Ya Li, Mingliang Gu, Jianhua Tao, Linlin Chao, Shanfeng Liu, "Combining Prosodic and Spectral Features for Mandarin Intonation Recognition" The 9th International Symposium on Chinese Spoken Language Processing2014 ISCSLP),pp.497-500,September 12 - 14,2014Singpore

88)   Wei Bao, Ya Li, Mingliang Gu, Minghao Yang, Hao Li, Linlin Chao, Jianhua Tao, "Building a Chinese Natural Emotional Audio-visual Database" 2014 International Conference on Signal ProcessingICSP 2014),pp.583-587Oct 19-23HangzhouChina

89)   Wei Lai,Ya Li,Hao Che,Shanfeng Liu,Jianhua Tao,Xiaoying Xu, "Final Lowering Effect in Questions and Statements of Chinese Mandarin Based on a Large-scale Natural Dialogue Corpus Analysis" SPEECH PROSODY 2014,May 20-23,PP:653-657,Dublin Ireland.

90)   Wei Lai, Ya Li, Hao Che, Shanfeng Liu, Jianhua Tao, "PHONOLOGICAL INFLUENCES ON THE REALIZATION OF FINAL LOWERING" The 17th Oriental COCOSDAPP:83-88,Sept 10-12Phuket, Thailand

91)   张大伟,杨明浩,陶建华, "面向X光发音视频的舌位轮廓自动提取方法" 《计算机辅助设计与图形学学报》,Apr.2014,Vol.26,No.4,pp.528-536

92)   杨明浩、陶建华、李昊、巢林林, "面向自然人机交互的多通道人机对话系统" 《计算机科学》,Oct.2014, Vol.41,No10pp 12-18

93)   袁雯, 赖玮, 许小颖, 李雅, 陶建华, "汉语特殊疑问句中焦点重音分布兼论语法、语义因素对特殊疑问句焦点重音的影响" 第十一届中国语音学学术会议,2014.08.08-08.10,新疆,乌鲁木齐.

94)   高廷丽,陶建华,杨明浩,张大伟, 巢林林,李昊,车浩,李雅,刘斌, "面向自然交互的多通道人机对话系统中答句自动生成方法研究" 第十届全国和谐人机环境联合学术会议,2014.09.13-09.14,北京.

95)   Minghao Yang, Jianhua Tao, Dawei Zhang, "Extraction of Tongue Contour in X-ray Videos" 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2013) ,May 26 - 31, 2013, Vancouver, Canada, PP.1094-1098.

96)   Hao Li, Minghao Yang, Jianhua Tao, "Speaker-Independent Lips and Tongue Visualization of vowels" 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2013), May.26 - 31, 2013,Vancouver, Canada,PP.8106-8110.

97)   Linlin Chao, Jianhua Tao, Minghao Yang, "Combining Emotional History Through Multimodal Fusion Methods" Asia Pacific Signal and Information Processing Association(APSIPA 2013), Oct.29-Nov.1 2013, Taiwan, China.

98)   Linlin Chao, Jianhua Tao, Minghao Yang, "Bayesian Inference based Temporal Modeling for Naturalistic Affective Expression Classification" The 5th International Conference on Affective Computing and Intelligent Interaction (ACII2013),Sep.2-5, 2013, Geneva, Switzerland.

99)   Yang Wang, Jianhua Tao, Minghao Yang, Ya Li, "Extended Decision Tree with OR Relationship for HMM-based Speech Synthesis" The 2nd Asian Conference on Pattern Recognition (ACPR2013), Nov.5-8, 2013, pp.225-229, Japan.

100) Ran Zhang, Jianhua Tao, Ya Li, Zhengqi Wen, "A Novel Unit Selection Method for Concatenation Speech System Using Similarity Measure" 16th International Oriental COCOSDA Conference, Oct.25-28, 2013, Gurgaon, India.

101) Chehao,Jianhua Tao, "Stress Prediction for Mandarin Text-to-Speech System Using Discourse Context Feature" 16th International Oriental COCOSDA Conference, Nov.25-28, 2013, Gurgaon, India.

102) Xiaoying Xu , Jianhua Tao, Ya Li, "On Constructing a Chinese Task-oriental Subjectivity Lexicon" The 14th Chinese Lexical Semantics Workshop, May 10-13, 2013, Zhengzhou.

103) 刘斌,陶建华,莫福源, "面向窄带通信的极低速率语音编码算法研究" 信号处理,2013Vol 29 No.9pp.1134-1141.

104) 刘敏,张劲松,李雅,陶建华,段日成, "斜率相关参数对双音节阳平词的重音感知的影响" 清华大学学报(自然科学版)2013No.6pp843-847.

105) 杨明浩,陶建华,李昊,巢林林, "面向自然交互的多通道人机对话系统" 2013年全国和谐人机环境联合学术会议,2013.09.26--09.28,南昌.

106) 杨明浩,陶建华,李昊, "说话人无关的唇舌语音驱动可视化" 第十二届全国人机语音通讯学术会议,2013.08.05--08.07,贵阳.

107) 杨明浩,陶建华,张大伟,李昊, "基于X光的汉语单音节舌位轮廓运动数据库" 第十二届全国人机语音通讯学术会议,2013.08.05--08.07,贵阳.

108) 刘善峰,李雅,陶建华, "基于词位信息的HMM中文分词算法" 第十二届全国人机语音通讯学术会议,2013.08.05--08.07,贵阳.

109) 高廷丽,陶建华,戴红亮,李雅, "傣文自动分词系统的设计与实现" 第十二届全国计算语言学会议,2013.10.10--10.11,苏州.

110) Minghao Yang, Jianhua Tao, Kaihui Mu, Ya Li, Jianfeng Che, "A Multimodal Approach of Generating 3D Human-like Talking Agent" Journal on Multimodal User Interfaces, 2012, 5(1), pp: 61-68.

111) Xiaoying Xu, Ya Li, Jianhua Tao, Xuefei Liu, "Automatic Parsing of the Metaphor Polarity for Opinion" O-COCOSDA 2012, Oral, 2012.12,P13-17, Macau, China.

112) Ya Li, Xuefei Liu, Xiaoying Xu, Jianhua Tao, "Assign Stress for Interrogative Sentences via Syntax Structure Mapping" Speech Prosody 2012,Oral, 2012.05,P167-170,Shanghai.

113) Che Hao,Jianhua Tao,Sifeng pan, "Letter-to-Sound Conversion Using Coupled Hidden Markov Models for Lexicon Compression" 2012 The International Committee for the Co-ordination and Standardization of Speech Databases and Assessment, Oral,2012.12,Macao,P141-144.

114) Zhegnqi Wen, Jianhua Tao and Che Hao, "Statistical Modification based Post-Filtering Technique for HMM-based Speech Synthesis" The 8th International Symposium on Chinese Spoken Language Processing, Poster, 2012.12,HongKong, pp.146-149.

115) Zhengqi Wen, Jianhua Tao and Horst-Ud0 Hain, "Pitch-Scaled Spectrum based Excitation Model for HMM-based Speech Synthesis" IEEE 11th International Conference on Signal Processing, Oral,2012.10,Beijing,pp.609-612.

116) Zhengqi Wen, and Jianhua Tao, "Prosody Modification for Vocoder Based on Amplitude Spectrum" Speech Prosody,6th International Conference,Poster,2012.05,Shanghai,pp.11-14.

117) Zhengqi Wen and Jianhua Tao, "Amplitude Spectrum based Excitation Model for HMM-based Speech Synthesis" 13th Annual Conference of the International Speech Communication Association, Oral,2012.09,USA.

118) Zhengqi Wen, Hideki Kawahara and Jianhua Tao, "Pitch-Scaled Analysis based Residual Reconstruction for Speech Analysis and Synthesis" 13th Annual Conference of the International Speech Communication Association, Oral,2012.09,USA.

119) Minghao Yang;Jianhua Tao;Hao Li;Mu Kai Hui, "Multimodal Emotion Estimation and Emotional Synthesize for Interaction Virtual Agent" IEEE CCIS 2012, Oral, 2012, Vol 1, Hangzhou, pp.239-244.

120) 杨明浩,陶建华,叶军涛,王阳生, "排除光流错误跟踪点的鲁棒方法" 计算机辅助设计与图形学学报, Jan.2012, Vol.24,No.1, pp.76-82.

121) Jianhua Tao, Shifeng Pan, Minghao Yang, Ya Li, Kaihui Mu and Jianfeng Che, "Utterance independent bimodal emotion recognition in spontaneous communication" Tao et al. EURASIP Journal on Advances in Signal Processing 2011, 2011.4.

122) Xiaoying Xu, Ya Li,Jianhua Tao, Yingchao Lu, "The Stability Analysis of Disyllabic Stress in Mandarin Speech" The 17th International Congress of Phonetic ences, ICPhS2011,2011.8,Hongkong.

123) Zhengqi WenJianhua Tao, "An Excitation Model Based on Inverse Filtering for Speech Analysis and Synthesis" 2011 IEEE International Workshop on Machine Learning for Signal Processing, 2011.9, Beijing.

124) Zhengqi WenJianhua Tao, "Inverse Filtering Based Harmonic plus Noise Excitation Model for HMM-based Speech Synthesis" 12thAnnual Conference of the International Speech Communication Association, Interspeech 201112thAnnual Conference of the International Speech Communication Association, Interspeech 2011.

125) Jianhua TaoShifeng Pan, Yoshihiko Nankaku, Keichi Tokuda, "Global Variance Modeling on Frequency Domain Delta LSP for HMM-based Speech Synthesis" The 35th International Conference on Acoustics, Speech, and Signal ProcessingICASSP2011, 2011.5, Prague, Czech, pp. 4716-4719.

126) Shifeng Pan, Jianhua Tao, Ya Li, "The CASIA Audio Emotion Recognition Method for Audio/Visual Emotion Challenge 2011" The 4rd International Conference on Affective Computing and Intelligent Interaction, ACII2011, 2011.8, Memphis, USA, pp.388-395.

127) Shifeng Pan, Jianhua Tao, Yang Wang, "A State Duration Generation Algorithm Considering Global Variance for HMM-based Speech Synthesis" Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2011, 2011.10, Xi'an.

128) Ya Li, Jianhua Tao, Xiaoying Xu, "Hierarchical Stress Modeling in Mandarin Text-to-Speech" 12th Annual Conference of the International Speech Communication Association, Interspeech 2011, 2011.8, Florence, Italy, pp. 2013-2016.

129) Minghao Yang, Jianhua Tao, Lihui Shi,Kaihui Mu, Jianfeng Che, "An Outlier Rejection Scheme For Optical Flow Tracking" 21th IEEE International Workshop on Machine Learning for Signal Processing, Beijing, China.

130) Kaihui Mu, Jianhua Tao, Minghao Yang, "Animating A Chinese Interactive Virtual Character" 21th IEEE International Workshop on Machine Learning for Signal Processing, Beijing, China.

131) 温正棋,陶建华, "基于逆滤波的激励建模" 第十一届全国人机语音通讯学术会议,2011.10.

132) 潘诗锋,陶建华,南角吉彦,德田惠一, "HMM语音合成中结合频域Delta LSP整体方差的参数生成方法" 第十一届全国人机语音通讯学术会议,2011.10.

133) 刘方舟,周游,陶建华, "CART模型指导TBL算法预测语调短语" 清华学报(自然科学版)2011年,Vol 51 No.9, pp.pp.1226-1229.

134) 陶建华,杨明浩,李雅,潘诗锋,穆凯辉, "多模态融合的人机对话系统" 中国计算机学会通讯,2011年,第11期,pp:30-38.

135) 卢颖超, 李雅, 陶建华, 许小颖, "连续语流中重音标注和大规模重音语料库建设" 清华学报(自然科学版)2011年,Vol 51 No.9, pp.1271-1275.

136) 李雅,潘诗锋,陶建华, "采用重音调整模型的HMM语音合成系统" 清华学报(自然科学版)2011年,Vol 51 No.9, pp.1171-1175.

137) 李雅, 卢颖超, 许小颖, 陶建华, "连续语流中韵律层级和调型组合对重音感知的影响" 清华学报(自然科学版)2011年,Vol 51 No.9, pp.1239-1243.

138) Jianhua Tao, Meng Zhang, Jani Nurminen, Jilei Tian, Xia Wang, "Supervisory Data Alignment for Text-independent Voice Conversion" IEEE Transactions on Audio, Speech and Language Processing (IEEE Trans. ASLP), Vol. 18, No. 5, July 2010, pp 932-943 .

139) Shifeng Pan, Meng Zhang, Jianhua Tao, "A Novel Hybrid Approach for Mandarin Speech Synthesis" Interspeech2010, Japan, Sep. 2010, pp 182-185 .

140) Ya Li, Jianhua Tao, Meng Zhang, Shifeng Pan, Xiaoying Xu, "Text-based Unstressed Syllable Prediction in Mandarin" Interspeech2010, Japan, Sep. 2010, pp 1752-1755 .

141) Ya Li, Shifeng Pan, Jianhua Tao, "HMM-based Speech Synthesis with a Flexible Mandarin Stress Adaptation Model" International Conference on Signal Processing (ICSP2010), Oct. 2010, pp 625-628 .

142) Kaihui Mu, Jianhua Tao, Jianfeng Che, Minghao Yang, "Mood Avatar: Automatic Text-Driven Head Motion Synthesis" International Conference on Multimodal Interfaces (ICMI2010), Nov. 2010 .

143) Kaihui Mu, Jianhua Tao, Jianfeng che, Minghao Yang, "Real-Time Speech-Driven Lip Synchronization" 4th International Universal Communication Symposium (IUCS2010), Oct. 2010, pp 377-381 .

144) Jianhua Tao, Kaihui Mu, Jianfeng Che, Ya Li, Zhengqi Wen, Shifeng Pan, Lixing Huang, Le Xin, "Audio-Visual Based Emotion Recognition with the Balance of Dominances" International Conference on Artificial Intelligence (ICAI1010), Oct. 2010, pp 100-110 .

145) Jianfeng Che, Jianhua Tao, Xingang Wang, Kaihui Mu, Hongtao Li, "Feature-based Multi-style Cartoon System" International Conference on Audio,Language and Image Processing (ICALIP2010), Nov. 2010 .

146) Xiaoying Xu, Jianhua Tao, Ling Zhang,Yingchao Lu, "The Duration Analysis of the Checked Tone in Cantonese Speech" International Symposium on Chinese Spoken Language Processing (ISCSLP2010), Nov. 2010, pp 459-464 .

147) Peter Khooshabeh, Jonathan Gratch, Lixing Haung, Jianhua Tao, "Does culture affect the perception of emotion in virtual faces?" 7th Symposium on Applied Perception in Graphics and Visualization (APGV '10), July 2010, pp 165 .

148) 王志明, 陶建华, "人脸遮挡区域检测与重建" 计算机研究与发展, 2010, 47(1), pp 16-22 .

149) 李雅, 卢颖超, 许小颖, 陶建华, "连续语流中韵律层级和调型组合对重音感知的影响" 第九届中国语音学学术会议(PCC2010), 20105月,天津.

150) 车建峰,陶建华,王欣刚,穆凯辉, "基于人脸特征的多风格卡通系统" 第十届中国虚拟现实大会(ChinaVR'2010), 201010月,上海.

151) Jian Yu, Jianhua Tao, "A Novel Prosody Adaptation Method for Mandarin Concatenation Based Text-to-Speech System"  Journal of Acoustical ence and Technology, Vol. 30, No.1, January 2009, pp.33-41.

152) Jianhua Tao, Le Xin, Panrong Yin, "Realistic Visual Speech Synthesis based on Hybrid Concatenation Method"  IEEE Transactions on Audio, Speech and Language Processing (IEEE Trans. ASLP), Vol. 17, No. 3, March 2009, pp 469-477.

153) Meng Zhang, Jianhua Tao, Jani Nurminen, Jilei Tian, Xia Wang, "Phoneme Cluster Based State Mapping for Text-Independent Voice Conversion"  34th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP2009, April 2009, Taipei, China.

154) Jianhua Tao, Ya Li, Shifeng Pan, "A Multiple Perception Model on Emotional Speech"   The 3rd International Conference on Affective Computing and Intelligent Interaction, ACII09, Sep. 2009, Amsterdam, Netherlands.

155) Xiaoying Xu, Ya Li, Liping Hu, Jianhua Tao, "Categorizing Terms’ Subjectivity and Polarity Manually for Opinion Mining in Chinese"  The 3rd International Conference on Affective Computing and Intelligent Interaction, ACII09, Sep. 2009, Amsterdam, Netherlands.

156) Hongjun Sun, Jianhua Tao, Huibin Jia, "Dimension Reducing of LSF parameters Based on Radial Basis Function Neural Network"   INTERSPEECH 2009, Sep. 2009, Brighton, UK.

157) Huibin Jia, Jianhua Tao, "Prosody Modeling for Mandarin Exclamatory Speech"   2009 IEEE International Conference on Multimedia and Expo ICME 2009, June 2009, New York, US.

158) Jianhua Tao, Fang Zheng, Aijun Li, Ya Li, "Advances in Chinese Natural Language Processing and language resources"   O-COCOSDA2009, Aug. 2009, Xinjiang, China.

159) 何鹏, 陶建华, "基于Sobolev 空间序列特征值问题的自然图像小尺度模式分析自动化学报, Vol. 35, No. 12200912月,1568-1573. .

160) 贾惠彬, 于剑, 陶建华, "拼接语音合成系统中的韵律自适应研究"   第十届全国人机语音通讯学术会议, NCMMSC 2009, 20098, 新疆 .

161) Jianhua Tao, Tieniu Tan (Eds), "Affective Information Processing"  UK: Springer Book,354 pages, Nov. 2008, ISBN:978-1-84800-305-7.

162) Meng Zhang, Jianhua Tao, Xia Wang, Jilei Tian, "Text-Independent Voice Conversion based on State Mapped Codebook"  33rd IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP2008, March 2008, Las Vegas, US, pp.4605-4608 .

163) Fangzhou Liu, Jianhua Tao, Qing Shi, "Tree-Guided Transformation-Based Homograph Disambiguation in Mandarin TTS System"  33rd IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP2008, March 2008, Las Vegas, US, pp.2657-4660 .

164) Huibin Jia Jianhua Tao, Xia Wang, "Prosody Variation: Application to Automatic Prosody Evaluation of Mandarin Speech"   Speech Prosody 2008, May. 2008, Campinas, Brazil.

165) Jianhua Tao, Jian Yu, Lixing Huang, Fangzhou Liu, Huibin Jia, Meng Zhang, "The WISTON Text to Speech System for Blizzard 2008"  The Blizzard Challenge 2008 workshop, Oct.2008.

166) Jianhua Tao, Fangzhou Liu, Meng Zhang, Huibin Jia, "Design of Speech Corpus for Mandarin Text to Speech"  The Blizzard Challenge 2008 workshop, Oct.2008.

167) Meng Zhang, Jianhua Tao, Huibin Jia, Xia Wang, "Improving HMM Based Speech Synthesis by Reducing Over-Smoothing Problems"  The 6th International Symposium on Chinese Spoken Language Processing, ISCSLP2008, Dec, 2008. Kunming, pp17-20.

168) Yi Zhang, Jianhua Tao, "Prosody Modification on Mixed-Language Speech Synthesis"   The 6th International Symposium on Chinese Spoken Language Processing, ISCSLP2008, Dec, 2008. Kunming, pp253-256 .

169) Fangzhou Liu, Huibin Jia, Jianhua Tao, "A Maximum Entropy Based Hierarchical Model for Automatic Prosodic Boundary Labeling In Mandarin"   The 6th International Symposium on Chinese Spoken Language Processing, ISCSLP2008, Dec, 2008. Kunming, pp257-260 .

170) Zhe Zhang, Lixing Huang, Jianhua Tao, "Unit Feature Based Pruning of Large-Scale Speech Corpus Using Decision Tree"  International Conference on Signal Processing, ICSP2008, Oct.2008, Beijing, pp719-722 .

171) Xiaoyin Xu, Jianhua Tao, "Categorizing Emotional Vocabularies in Chinese Natural Language Communication" O-COCOSDA2008, Nov.2008, Nara, Japan .

172) Mingyu You, Guo-Zheng Li, Luonan Chen, Jianhua Tao, "A Novel Classifier Based on Enhanced Lipschitz Embedding for Speech Emotion Recognition" 4th International Conference on Intelligent Computing, ICIC (1) 2008, Shanghai, pp:482-490.

173) 黄力行,辛乐,赵礼悦,陶建华, "自适应权重的双模态情感识别" 清华大学学报(自然科学版)2008 年第48 卷第S1 期,pp715-719.

174) 于剑、黄力行、陶建华, "汉语对话语气韵律建模方法的研究" 清华大学学报(自然科学版)2008 年第48 卷第S1 期,pp658-663.

175) 陶建华、黄力行、 于剑, "基于情感矢量的情感语音自动感知模型" 中国语音学报(商务出版社)2008 年第1 卷第1.

176) 贾惠彬、陶建华, "朗读语气韵律可变性分析及韵律自动评价初探" 第八届中国语音学会议,20084.

177) Jianhua Tao, Panrong Yin, "Speech Driven Face Animation Based on Dynamic Concatenation Model" International Journal of Information and Computational ence, v 4, n 1, March, 2007, p 271-280.

178) Jian Yu, Meng Zhang, Jianhua Tao, Xia Wang, "A novel hmm-based TTS system using both continuous HMMs and discrete HMMs" 32nd IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP2007, Hawaii .

179) Mingyu You, Chun Chen, Jiajun Bu, Jia Liu, Jianhua Tao, "Manifolds based Emotion Recognition in Speech" International Journal of Computational Linguistics & Chinese Language Processing, Vol. 12, No. 1, March 2007, pp49-64 .

180) Jian Yu, Lixing Huang, Jianhua Tao, Xia Wang, "Modeling Incompletion Phenomenon in Mandarin Dialog Prosody" Interspeech2007,August 2007, Antrewp.

181) Huibin Jia Jianhua Tao, "Automatic Prosody Quality Evaluation of Mandarin Speech" O-COCOSDA2007, Dec. 2007, Hanoi, Vietnam.

182) Xia Wang, Aijun Li, Jianhua Tao, "An Expressive Speech Corpus of Standard Chinese" O-COCOSDA2007, Dec. 2007, Hanoi, Vietnam .

183) Panrong Yin, Liyue Zhao, Lixing Huang, Jianhua Tao, "Expressive Face Animation Synthesis based on Dynamic Mapping Method" the 2nd International Conference on Affective Computing and Intelligent Interaction, ACII2007, Sep.2007, Lisbon.

184) Lixing Huang, Le Xin, Liyue Zhao, Mi Zhou, Jianhua Tao, "Combining Audio and Video by Dominance in Bimodal Emotion Recognition"  the 2nd International Conference on Affective Computing and Intelligent Interaction, ACII2007, Sep.2007, Lisbon .

185) Marc Schr?der, Laurence Devillers, Kostas Karpouzis, Jean-Claude Martin, Catherine Pelachaud, Chris, "What Should a Generic Emotion Markup Language Be Able to Represent?, " the 2nd International Conference on Affective Computing and Intelligent Interaction, ACII2007, Sep.2007, Lisbon.

186) Liyue Zhao, Jianhua Tao, "Fast Facial Feature Tracking with Multi-Cue Particle Filter" Image and Vision Computing New Zealand, IVCNZ2007, Hamilton, New Zealand .

187) Le Xin, Jianhua Tao, Tieniu Tan, "Dynamic Audio-Visual Mapping using Fused Hidden Markov Model Inversion Method" IEEE International Conference on Image Processing, ICIP2007, Sep.2007, pp293-296.

188) Zhiming Wang, Jianhua Tao, "Reconstruction of Partially Occluded Face by Fast Recursive PCA" ,International Conference on Computational Intelligence and Security, Dec. 2007, Harbin .

189) Zhiming Wang, Jianhua Tao, , "Remove Unknown Face Occlusion by Fuzzy Principal Component Analysis" CCPR2007, Beijing.

190) Jia Liu, Chun Chen, Jiajun Bu, Mingyu You, Jianhua Tao, "Speech Emotion Recognition Based on a Fusion of All-Class and Pairwise-Class Feature Selection"  International Conference on Computational ence (1) 2007: 168-175.

191) 董宏辉、陶建华、徐波, "基于约束模型的韵律短语预测" 中文信息学报,2007, 21(01),pp54-59.

192) 于剑、张蒙、陶建华、王霞, "一种混合使用连续HMM和离散HMMHTS合成系统" 《信号处理》,第十三届全国信号处理学术年会(CCSP),2007-08,济南 .

193) 刘方舟、陶建华, "基于最大熵模型的多音字消歧第九届全国人机语音通讯学术会议(NCMMSC2007, 2007.10,黄山 .

194) 张蒙,陶建华, "基于共振峰增强训练算法的HTS研究与改进" 第九届全国语音通讯学术会议(NCMMSC2007),2007 10,黄山 .

195) Jianhua Tao, Yongguo Kang, Aijun Li, "Prosody conversion from neutral speech to emotional speech" IEEE Transactions on Audio, Speech, and Language Processing (IEEE Trans. ASLP), Vol. 14, No. 4, July 2006, pp1145-1154.

196) Jian Yu, Wanzhi Zhang and Jianhua Tao, "A new pitch generation model based on internal dependence of pitch contour for mandarin TTS system" ICASSP 2006, Toulouse, France .

197) Yongguo Kang, Jianhua Tao, Bo Xu, "Applying Pitch Target Model to Convert F0 Contour for Expressive Mandarin Speech Synthesis " ICASSP 2006, Toulouse,France .

198) Mingyu You, ChunChen, JiajunBu, JiaLiu,JianhuaTao , "Emotion recognition from noisy speech"  IEEE International Conference on Multimedia and Expo, ICME2006, Canada.

199) Mingyu You, ChunChen, JiajunBu, JiaLiu, JianhuaTao, "Emotional Speech Analysis on onlinear Manifold" International Conference on Pattern Recognition, ICPR2006, Hongkong.

200) Donghui Dong, Jianhua Tao, Bo Xu, "Prosodic Word Prediction using a Maximum Entropy Approach" International Symposium on Chinese Spoken Language Processing, Lecture Notes of Computer ence, ISCSLP2006, Singapore.

201) Jian Yu, Jianhua Tao, "Pitch Prediction for Mandarin TTS with Mutual Prosodic Constraint" International Symposium on Chinese Spoken Language Processing, ISCSLP2006, Singapore.

202) Jianhua Tao, Lixing Huang, Yongguo Kang, Jian Yu, "The Friendliness Perception of Dialogue Speech"  2006 International Conference on Speech Prosody, May 2006, Germany.

203) Min Chu, Honghui Dong, Jianhua Tao, "A Perceptual Study on Variability in Break Allocation within Chinese Sentences" 2006 International Conference on Speech Prosody, May 2006, Germany.

204) Nick Campbell, Laurence Devillers, Ellen Douglas-Cowie, Veronique Auberge, Anton Batliner, and Jian, "Resources for the Processing of Affect in Interactions" LREC2006, May 2006, Italy.

205) Yanhong Wu,Jianhua Tao, Jilun Lu, "The Design of Corpus for Interrogative Speech Synthesis" The 2006 Oriental COCOSDA, December 2006, MALAYSIA .

206) Wang Zhiming, Tao Jianhua, "A fast implementation of adaptive histogram equalization" the 8th International Conference on Signal Processing, December 2006, Guilin, pp1330-1334 .

207) Ren-Hua Wang, Sin-Horng Chen, Jianhua Tao, Min Chu, "MANDARIN TEXT-TO-SPEECH SYNTHESIS" Chapter 5 of the book Advanced Chinese Spoken Language Processing, published in December 2006 .

208) Hsiao-Chuan Wang, Thomas Fang Zheng, and Jianhua Tao, "CSLP CORPORA AND LANGUAGE RESOURCES" Chapter 23 of the book Advanced Chinese Spoken Language Processing, published in December 2006.

209) 康永国、双志伟、陶建华、张维, "基于混合映射模型的语音转换算法研究" 《声学学报》, 200611月, Vol.31,No.6pp555-562 .

210) 陶建华、康永国, "情感语音韵律自动生成方法的研究" 《声学技术》,200610.

211) 王志明、陶建华, "文本-视觉语音合成综述" 《计算机研究与发展》, 200643(1): 145~152 .

212) 陶建华、董宏辉, "韵律短语的语法约束研究" 中国中文信息学会二十五周年学术会议,200611.

213) 董宏辉、陶建华, "浅析汉语韵律短语中的稳定结构" 第七届中国语音学学术会议,200611.

214) 于剑、陶建华, "对音节之间相互制约关系的研究" 第七届中国语音学学术会议,200611 .

215) 伍艳红、陶建华、路继伦, "汉语疑问语调的韵律分析" 第七届中国语音学学术会议,200611 .

216) 张凌、陶建华、许小颖, "广州话入声字时长特性分析" 第七届中国语音学学术会议,200611.

217) Jian Yu, Jianhua Tao, "The Pause Duration Prediction for Mandarin Text-to-Speech System"  2005 IEEE International Conference on Natural Language Processing and Knowledge ngineering (IEEE NLP-KE 2005),Wuhan,China,pp.204-208,2005, LSBN:0-7803-9361-9 .

218) Panrong Yin, Jianhua Tao, "Dynamic mapping method based speech driven face animation system" The First International Conference on Affective Computing & Intelligent Interaction (ACII2005),Beijing,China, pp.755-763,2005,ISSN 0302-9743  .

219) Yonglin Li, Jianhua Tao, "Personalized Facial Animation Based on 3D Model Fitting from Two Orthogonal Face Images" the first International Conference on Affective Computing and Intelligent Interaction ,Beijing,China,pp.996-1003,2005, ISSN 0302-9743 .

220) Yongguo Kang, Zhiwei Shuang ,Jianhua Tao, "A hybrid GMM and codebook mapping method for spectral conversion" The First International Conference on Affective Computing & Intelligent Interaction (ACII2005),Beijing,China,pp.303-310,2005, ISSN 0302-9743 .

221) Le Xin,Qiang Wang, Jianhua Tao, "Automatic 3D Face Modeling from Video" Proc. of the Tenth IEEE International conference on computer vision (ICCV2005)Beijing China ,Vol.2.

222) Honghui Dong, Jianhua Tao, Bo Xu, "Chinese Prosodic Phrasing with a Constraint-based Approach" INTERSPEECH 2005-EUROSPEECHLisbon, Portugal .

223) Honghui Dong, Jianhua Tao,Bo Xu, "Prosodic Word Prediction Using the Lexical Information" 2005 IEEE International Conference on Natural Language Processing and Knowledge EngineeringWuhan, China,pp.189-193,2005,LSBN:0-7803-9361-9 .

224) Honghui Dong, Jianhua Tao, "Length Optimized Chinese Prosodic Phrasing Model" Proceedings of the International Conference on Chinese Computing 2005, pp.48-53,2005, Singapore .

225) Jianhua Tao,Yongguo Kang, "Features Importance Analysis for Emotional Speech Classification" The First International Conference on Affective Computing & Intelligent Interaction (ACII2005), Beijing,China,pp.449-457,2005 ,ISSN 0302-9743 .

226) Jianhua Tao,Tieniu Tan, "Affective Computing:A review" The First International Conference on Affective Computing & Intelligent Interaction (ACII2005),Beijing,China,pp.981-995,2005, ISSN 0302-9743 .

227) Jianhua Tao,jianyu Yongguo Kang, "An Expressive Mandarin Speech Corpus" The International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA2005, Bali Island, Indonesia,2005 .

228) 胡伟湘、董宏辉、陶建华、黄泰翼, "汉语朗读话语重音自动分类研究" 中文信息学报,Vol.19, No.6, pp.78-83,2005,ISSN 1003-0077.

229) 康永国、陶建华、徐波, "基于频域子带的语音调幅-调频分解模型" 信号处理,Vol.21,No.4,pp.216-219,2005,ISSN1003-0530 .

230) 康永国、双志伟、陶建华, "高斯混合模型和码本映射相结合的语音转换算法" 声学技术,Vol.24,pp.293-297,2005,ISSN1000-3630  .

231) 张皖志、陶建华, "基于声韵母基元的嵌入式中文语音合成系统" 信号处理,Vol.21.No.4,pp.220-222,2005,ISSN1003-0530 .

232) 张皖志、陶建华, "基于声韵母基元声学特征的中文TTS系统中音库的量化压缩策略" 声学技术, Vol,24, pp.321-325, 2005,ISSN1000-3630 .

233) Jianhua Tao and Tieniu Tan, "Emotional Chinese Talking Head System"  ICMI 200410pages:273-280  .

234) Jianhua Tao, "Context Based Emotion Detection from Text Input" 8th International Conference on Spoken Language Processing, ICSLP2004, Jeju, 4-8,Oct.2004,pages:1337-1340 .

235) Jianhua Tao, "Rhymth Correlation of Speech Synthesis System" ISCSLP2004, pages:221-224 .

236) Jianhua Tao, "Acoustic and Linguistic Information Based Chinese Prosodic Boundary Labelling" , "" , Lecture Notes of Artificial Intelligence, Springer, 2004,9 .

237) Jianhua Tao and Yongguo Kang,, "Multi-Source Based Acoustic Model for Speech Synthesis"  ICSP2004 Vol.I of III,pagese:621-625  .

238) Honghui Dong, Jianhua Tao , Bo Xu, "Grapheme-to-Phoneme Conversion in Chinese TTS System" ISCSLP2004,pages:165-168.

239) Yongguo Kang, Jianhua Tao, Bo Xu, "A New Multicomponent AM-FM Demodulation with Predicting Frequency Boundaries and Its Application to Formant Estimation" Interspeech2004, Oct. 2004, Jeju, pp 1105-1108.

240) 陶建华、康永国, "基于多元激励的高质量语音合成声学模型" 中文信息学报,Vol.18, No.3,2004, pp73-80.

241) 许小颖、陶建华, "汉语情感系统中情感划分的研究" 第一届中国情感计算及智能交互会议,北京,200312.

242) 陶建华、许小颖, "面向情感的语音合成系统" 第一届中国情感计算及智能交互会议,北京,200312.

发表著作
Jianhua Tao, Tieniu Tan (Eds), Affective Information Processing, UK: Springer Book,354 pages, Nov. 2008, ISBN:978-1-84800-305-7

科研活动

   
科研项目
(1) 语音自适应模型,主持,其他级,2013-01--2013-12
(2) 语音产生过程的神经生理建模与控制,主持,国家级,2013-01--2017-12
(3) 基于影像和语音分析的发音器官运动可视化,主持,国家级,2013-01--2016-12
(4) 语音交互平台,主持,其他级,2013-01--2014-12
(5) 基于维度模型的情感语音建模及生成方法研究,主持,国家级,2013-01--2015-12
(6) 网络音视频内容分析与处理,主持,部委级,2012-05--2014-04
(7) 对话管理为中心的双向多模态人机交互研究,主持,国家级,2009-01--2013-12