报告正文

Size: px

Start display at page:

Download "报告正文"

观寇元
5 years ago
Views:

1 个人简历凌震华, 男, 生于 1979 年 8 月, 安徽省合肥市人中国科学技术大学信号与信息处理专业博士, 现任中国科学技术大学电子工程与信息科学系副教授博士生导师主要研究方向为语音信号处理教育经历 2005/9-2008/6 中国科学技术大学, 信号与信息处理, 博士, 导师 : 王仁华 2002/9-2005/6 中国科学技术大学, 信号与信息处理, 硕士, 导师 : 王仁华 1996/9-2002/6 中国科学技术大学, 电子信息工程, 学士, 导师 : 王仁华工作经历 2011/1 - 至今中国科学技术大学, 语音及语言信息处理国家工程实验室 / 电子工程与信息科学系, 副教授 2012/8-2013/8 美国华盛顿大学, 电子工程系, 访问学者 2008/7 2010/12 中国科学技术大学 / 科大讯飞股份有限公司, 博士后 2007/ /4 英国爱丁堡大学, 语音技术研究中心, 访问学者科研项目项目类别批准号名称起止年月金额 ( 万元 ) 项目状态负责或参加工信部电子信息产业发展基金工信部财 [2014]425 号面向少数民族语言的智能语音技术及系统研发 2014/ / 在研子课题负责人安徽省科技攻关项目面向高级人工智能领域的类人智能关键技术及系统研发 2014/ / 在研负责国家自然科学基金青年 - 面上连续资助项目融合语音产生机理与统计声学建模的层次化语音合成方法 2013/ /12 80 在研负责国家自然科学基金委 - 英国爱丁堡皇家学会国际合作交流项目用于灵活可控语音合成的发音动作参数 - 声学参数联合建模方法研究 2011/ / 结题负责

2 国家自然科学基金青年科学基金项目结合发音动作参数的统计建模语音合成方法研究 2010/ /12 19 结题负责中国博士后科学基金面上项目基于合成语音质量评估的语音合成方法研究 2009/ /10 3 结题负责工信部电子信息产业发展基金工信部财 [2013]472 号基于自然语音人机交互的信息搜索系统研发和产业化 2013/ / 结题参加科技部 973 前期研究专项 2012CB 声纹识别及声音转换深度学习理论与方法 2012/ /12 61 结题参加科研获奖智能语音交互关键技术及应用开发平台, 国家科技进步奖二等奖 ( 总排名第 9, 本单位排名第 3), 2011 年 IEEE 信号处理学会最佳青年作者论文奖 (IEEE Signal Processing Society Young Author Best Paper Award), 2010 年智能语音交互关键技术及应用平台, 安徽省科技进步奖一等奖 ( 排名第 9), 2008 年面向口语学习的中英文智能语音评测与学习技术, 中国电子学会电子信息科学技术奖二等奖 ( 排名第 7), 2008 年学术兼职 IEEE/ACM Transactions on Audio, Speech, and Language Processing(IEEE/ ACM TASLP) 副编辑 (Associate Editor), 2014/ /01 国际语音通信协会 (ISCA) 通讯委员会委员 (Communication Committee Member) 中国语言学会语音学分会学术委员会委员全国人机语音通讯学术会议常设机构委员会委员 2015 年口语语音资料库协调暨标准化国际研讨会东方分会和亚太口语语言研究和评价会议 (Oriental COCOSDA/CASLRE) 科学委员会 (Scientific Committee) 成员 2015 年 IEEE 信号与信息处理中国高峰会议 (ChinaSIP) 技术程序委员会 (Technical Program Committee) 成员 2015 年全国人机语音通讯学术会议分会主席 2014 年 IEEE 声学语音和信号处理国际会议 (ICASSP) 分会主席 (Session

3 Chair) 2014 年 ISCA 年会 (Interspeech) 会议分会主席 (Session Chair) 2014 年 IEEE 信号与信息处理中国高峰会议 (ChinaSIP) 技术程序委员会 (Technical Program Committee) 成员 2014 年中文口语处理国际研讨会 (ISCSLP ) 程序委员会 (Program Committee) 成员 2013 年 ISCA 语音合成研讨会 (SSW) 程序委员会 (Program Committee) 成员 2012 年语音韵律国际会议 (ICSP) 科学委员会 (Scientific Committee) 成员 2012 年 ISCA 年会 (Interspeech) 会议分会主席 (Session Chair) IEEE 会员 ; 国际语音通信协会 (ISCA) 会员任以下期刊审稿人 Proceedings of the IEEE The Journal of Selected Topics in Signal Processing IEEE/ACM Transactions on Audio Speech and Language Processing IEEE Transactions on Neural Networks and Learning Systems IEEE Transactions on Fuzzy Systems Computer Speech and Language Speech Communication IEICE Transactions on Information and Systems EURASIP Journal on Audio, Speech, and Music Processing Information Sciences Journal of Signal Processing Systems 特邀报告邀请单位报告名称报告时间及地点第 15 届日本口语处理研讨会微软研究院英国爱丁堡大学 Acoustic Modeling Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis and Voice Conversion HMM-based Speech Synthesis: Fundamentals and Its Recent Advances Automatic Error Detection for Unit Selection Speech Synthesis Using Human Feedbacks 2013/12 日本东京 2012/09 美国雷蒙德 2011/08 英国爱丁堡

4 发明专利专利名称专利号授权日期一种基于受限玻尔兹曼机的语音合成方法一种说话人声音转换方法一种语音信号增强系统和方法基于声学统计模型的单元挑选语音合成方法语音合成方法及装置一种个性化歌唱语音的合成方法一种结合自然样本挑选与声学参数建模的语音合成方法基于线谱频率及其阶间差分参数的频谱建模与语音增强方法一种结合高层描述信息和模型自适应的说话人转换方法 X 发表论文国际期刊论文 (* 通讯作者 ) [1] Ya-Jun Hu, and Zhen-Hua Ling*, "DBN-based Spectral Feature Representation for Statistical Parametric Speech Synthesis," IEEE Signal Processing Letters, accepted. [2] Xin Wang, Zhen-Hua Ling*, and Li-Rong Dai, "Concept-to-Speech Generation with Knowledge Sharing for Acoustic Modelling and Utterance Filtering," Computer Speech and Language, accepted. [3] Xiang Yin, Ming Lei, Yao Qian, Frank K. Soong, Lei He, Zhen-Hua Ling*, and Li-Rong Dai, "Modeling F0 Trajectories in Hierarchically Structured Deep Neural Networks," Speech Communication, vol. 76, pp , [4] Korin Richmond, Zhen-Hua Ling, and Junichi Yamagishi, "The use of articulatory movement data in speech synthesis applications: an overview Application of articulatory movements using machine learning algorithms ", Acoustical Science and Technology, vol. 36, no. 6, pp , [5] Ling-Hui Chen, Tuomo Raitio, Cassia Valentini-Botinhao, Zhen-Hua Ling, and Junichi Yamagishi, "A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 23, no. 11, pp , 2015.

5 [6] Ming-Qi Cai, Zhen-Hua Ling*, Li-Rong Dai, "Statistical Parametric Speech Synthesis Using a Hidden Trajectory Model", Speech Communication, vol. 72, pp , [7] Zhen-Hua Ling, Shi-Yin Kang, Heiga Zen, Andrew Senior, Mike Schuster, Xiao-Jun Qian, Helen Meng, Li Deng, "Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends," IEEE Signal Processing Magazine, vol. 32, no. 3, pp , [8] Su-Kui Xu, Si Wei, Zhen-Hua Ling*, Qian-Yong Gao, Li-Rong Dai, and Qing-Feng Liu, "A Statistical Modeling Approach to Automatic Evaluation of Mandarin Pronunciation", Journal of the Phonetic Society of Japan, vol. 19, no. 1, pp , [9] Jing-Jie Li, Ian V. McLoughlin, Li-Rong Dai, and Zhen-Hua Ling, "Whisper-to-speech conversion using restricted Boltzmann machine arrays," Electronics Letters, vol. 50, no. 24, pp , [10] Ling-Hui Chen, Zhen-Hua Ling*, Li-Juan Liu, and Li-Rong Dai, "Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 22, no. 12, pp , [11] Xian-Jun Xia, Zhen-Hua Ling*, Yuan Jiang, and Li-Rong Dai, "HMM-based Unit Selection Speech Synthesis Using Log Likelihood Ratios Derived from Perceptual Data", Speech Communication, vol , pp , [12] Chen-Yu Yang, Zhen-Hua Ling, and Li-Rong Dai, "Unsupervised Prosodic Labeling of Speech Synthesis Databases Using Context-Dependent HMMs", IEICE Transactions on Information and Systems, vol.e97-d, no.6, pp , [13] Zhen-Hua Ling, Li Deng, and Dong Yu, "Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis," IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 10, pp , [14] Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi, Articulatory Control of HMM-based Parametric Speech Synthesis using Feature-Space-Switched Multiple Regression, IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 1, pp , [15] Zhen-Hua Ling, and Li-Rong Dai, Minimum Kullback-Leibler Divergence Parameter Generation for HMM-based Speech Synthesis, IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 5, pp , [16] Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi, An analysis of HMM-based prediction of articulatory movements, Speech Communication, vol. 52, no. 10, pp , [17] Heng Lu, Zhen-Hua Ling, Li-Rong Dai, and Ren-Hua Wang, Cross-Validation and Minimum Generation Error based Decision Tree Pruning for HMM-based Speech Synthesis, Computational Linguistics and Chinese Language Processing, vol. 15, no. 1, pp , March [18] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, and Ren-Hua Wang, Integrating articulatory features into HMM-based parametric speech synthesis, IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 6, pp , 2009.

6 [19] Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-Hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, and Steve Renals, Robust speaker-adaptive HMM-based text-to-speech synthesis, IEEE Transactions on Andio, Speech and Language Processing, vol. 17, no. 6, pp , 国内期刊论文 [1] 孙晓辉, 凌震华, 戴礼荣, 融合自动检错的单元挑选语音合成方法研究, 数据采集与处理, 已接收. [2] 凌震华, 高丽, 戴礼荣, 基于目标逼近特征和双向联想贮存器的情感语音基频转换, 天津大学学报,vol. 48, pp , [3] 蔡明琦, 凌震华, 戴礼荣, 基于隐马尔科夫模型的中文发音动作参数预测方法研究, 数据采集与处理,vol. 29, no. 2, pp , [4] 宋阳, 凌震华, 戴礼荣, 基于合成质量预测的单元挑选语音合成优化方法研究, 清华大学学报 ( 自然科学版 ),vol. 53, no. 6, pp , [5] 陈凌辉, 凌震华, 戴礼荣, 基于话者无关模型的说话人转换方法, 模式识别与人工智能,vol. 26, no. 3, pp [6] 张元平, 凌震华, 戴礼荣, 刘庆峰, 一种改进的基于决策树的英文韵律短语边界预测方法, 计算机应用研究,vol. 29, no. 8, pp , [7] 刘海波, 李辉, 凌震华, 用于周期分解语音活动检测的基频提取方法研究, 中国科学技术大学学报,vol. 42, no. 2, pp , [8] 胡郁, 凌震华, 王仁华, 戴礼荣, 基于声学统计建模的语音合成技术研究, 中文信息学报,vol. 25, no.6, pp , [9] 杨辰雨, 朱立新, 凌震华, 戴礼荣, 基于 Viterbi 解码的中文合成音库韵律短语边界自动标注, 清华大学学报 ( 自然科学版 ),vol. 51, no. 9, pp , [10] 刘航, 凌震华, 郭武, 戴礼荣, 一种改进的跨语种语音合成模型自适应方法, 模式识别与人工智能,vol. 24, no. 4, [11] 卢恒, 凌震华, 雷鸣, 戴礼荣, 王仁华, 基于最小生成误差的 HMM 模型聚类自动优化, 模式识别与人工智能,vol. 23, no.6, pp , [12] 赵欢欢, 凌震华, 王仁华, 戴礼荣, 基于最大后验概率的语音合成说话人自适应, 数据采集与处理, vol. 25, no.4, pp , [13] 雷鸣, 凌震华, 戴礼荣, 基于感知加权线谱对距离的最小生成误差语音合成模型训练方法, 模式识别与人工智能,vol. 23, no.4, pp , [14] Ren-Hua Wang, Li-Rong Dai, Zhen-Hua Ling, and Yu Hu, Trainable unit selection speech synthesis under statistical framework, Chinese Science Bulletin, vol. 54, no. 11, pp , [15] 凌震华, 王仁华, 基于统计声学模型的单元挑选语音合成算法, 模式识别与人工智能, vol. 21, no. 3, 2008, pp [16] Wei Zhang, Zhen-Hua Ling, Guo-Ping Hu, and Ren-Hua Wang, A synthesis instance pruning approach based on virtual non-uniform replacements, Tsinghua Science and Technology, vol. 13, no. 4, pp , [17] 王仁华, 戴礼荣, 胡郁, 凌震华, 基于声学统计建模的新一代语音合成技术, 中国科学技术大学学报, vol. 38, no. 7, pp , 2008.

7 [18] 周斌, 戴礼荣, 凌震华, 王仁华, 一种自然语流的声源分析方法, 数据采集与处理, vol. 20, no. 3, pp , [19] 凌震华, 双志伟, 周斌, 王仁华, " 基于自适应加权谱内插的宽带语音编码算法," 数据采集与处理, vol. 20, no. 1, pp , [20] 朱东来, 王仁华, 凌震华, 李威, 基于隐马尔科夫模型的汉语韵律词基频模型, 声学学报, vol. 27, no. 6, pp , 国际会议论文 [1] Zhen-Hua Ling, Xiao-Hui Sun, Li-Rong Dai, and Yu Hu, "MODULATION SPECTRUM COMPENSATION FOR HMM-BASED SPEECH SYNTHESIS USING LINE SPECTRAL PAIRS," ICASSP 2016, accepted. [2] Xiang Yin, Zhen-Hua Ling, Ya-Jun Hu, and Li-Rong Dai, "MODELING SPECTRAL ENVELOPES USING DEEP CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS," ICASSP 2016, accepted. [3] Ya-Jun Hu, Zhen-Hua Ling, and Li-Rong Dai, "DEEP BELIEF NETWORK-BASED POST-FILTERING FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS," ICASSP 2016, accepted. [4] Xin Wang, Ming-Hui Dong, and Zhen-Hua Ling, "A FULL TRAINING FRAMEWORK OF CROSS-STREAM DEPENDENCE MODELLING FOR HMM-BASED SINGING VOICE SYNTHESIS," ICASSP 2016, accepted. [5] Qian Chen, Zhen-Hua Ling, Chen-Yu Yang, and Li-Rong Dai, "Automatic Phrase Boundary Labeling of Speech Synthesis Database Using Context-Dependent HMMs and N-Gram Prior Distributions", in Interspeech [6] Quan Liu, Hui Jiang, Si Wei, Zhen-Hua Ling, and Yu Hu, "LEARNING SEMANTIC WORD EMBEDDINGS BASED ON ORDINAL KNOWLEDGE CONSTRAINTS", in ACL [7] Yu Gu, and Zhen-Hua Ling, "Restoring High Frequency Spectral Envelopes Using Neural Networks for Speech Bandwidth Extension", in IJCNN, IEEE [8] Zheng-Chen Liu, Zhen-Hua Ling, and Li-Rong Dai, "LIP MOVEMENT GENERATION USING RESTRICTED BOLTZMANN MACHINES FOR VISUAL SPEECH SYNTHESIS", in ChinaSIP, pp , [9] Li-Juan Liu, Ling-Hui Chen, Zhen-Hua Ling, Li-Rong Dai, "SPECTRAL CONVERSION USING DEEP NEURAL NETWORKS TRAINED WITH MULTI-SOURCE SPEAKERS", in ICASSP, pp , [10] Ling-Hui Chen, Zhen-Hua Ling, Yi-Qing Zu, Run-Qiang Yan, Yuan Jiang, Xian-Jun Xia, Ying Wang, "The USTC System for Blizzard Challenge 2014", in Blizzard Challenge Workshop, [11] Ming-Qi Cai, Zhen-Hua Ling, and Li-Rong Dai, "Formant-Controlled Speech Synthesis Using Hidden Trajectory Model", in Interspeech, pp , [12] Xin Wang, Zhen-Hua Ling, and Li-Rong Dai, "Concept-to-Speech Generation by Integrating Syntagmatic Features into HMM-Based Speech Synthesis", in Interspeech, pp , 2014.

8 [13] Ling-Hui Chen, Zhen-Hua Ling, and Li-Rong Dai, "Voice Conversion Using Generative Trained Deep Neural Networks with Multiple Frame Spectral Envelopes", in Interspeech, pp , [14] Xiang Yin, Ming Lei, Yao Qian, Frank K. Soong, Lei He, Zhen-Hua Ling, and Li-Rong Dai, "Modeling DCT Parameterized F0 Trajectory at Intonation Phrase Level with DNN or Decision Tree", in Interspeech, pp , [15] Ling-Hui Chen, Tuomo Raitio, Cassia Valentini-Botinhao, Junichi Yamagishi, and Zhen-Hua Ling, "DNN-based stochastic postfilter for HMM-based speech synthesis", in Interspeech, pp , [16] Li Gao, Zhen-Hua Ling, Ling-Hui Chen, Li-Rong Dai, "Improving F0 Prediction Using Bidirectional Associative Memories and Syllable-Level F0 Features for HMM-based Mandarin Speech Synthesis", in ISCSLP, [17] Yu-Sheng Sun, Zhen-Hua Ling, Xiang Yin, Li-Rong Dai, "Integrating Global Variance of Log Power Spectrum Derived from LSPs into MGE Training for HMM-Based Parametric Speech Synthesis", in ISCSLP, [18] Xiang Yin, Zhen-Hua Ling, and Li-Rong Dai, "SPECTRAL MODELING USING NEURAL AUTOREGRESSIVE DISTRIBUTION ESTIMATORS FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS", in ICASSP, pp , [19] Li-Juan Liu, Ling-Hui Chen, Zhen-Hua Ling, and Li-Rong Dai, "USING BIDIRECTIONAL ASSOCIATIVE MEMORIES FOR JOINT SPECTRAL ENVELOPE MODELING IN VOICE CONVERSION", in ICASSP, pp , [20] Ling-Hui Chen, Zhen-Hua Ling, Yuan Jiang, Yang Song, Xian-Jun Xia, Yi-Qing Zu, Run-Qiang Yan, and Li-Rong Dai, "The USTC System for Blizzard Challenge 2013", in Blizzard Challenge Workshop, [21] Maria Astrinaki, Alexis Moinet, Junichi Yamagishi, Korin Richmond, Zhen-Hua Ling, Simon King, and Thierry Dutoit, "Mage - Reactive articulatory feature control of HMM-based parametric speech synthesis", in 8th ISCA Speech Synthesis Workshop, pp , [22] Ling-Hui Chen, Zhen-Hua Ling, Yan Song, and Li-Rong Dai, Joint spectral distribution modeling using restricted Boltzmann machines for voice conversion, in Interspeech, pp , [23] Korin Richmond, Zhen-Hua Ling, Junichi Yamagishi, Benigno Uria, On the Evaluation of Inversion Mapping Performance in the Acoustic Domain, in Interspeech, pp , [24] Zhen-Hua Ling, Li Deng, and Dong Yu, "Modeling Spectral Envelopes Using Restricted Boltzmann Machines for Statistical Parametric Speech Synthesis", in ICASSP, pp , [25] Chen-Yu Yang, Zhen-Hua Ling, and Li-Rong Dai, "Unsupervised Prosodic Phrase Boundary Labeling of Mandarin Speech Synthesis Database Using Context-Dependent HMM", in ICASSP, pp , [26] Xin Wang, Zhen-Hua Ling, and Li-Rong Dai, "Cross-Stream Dependency Modeling Using Continuous F0 Model For Hmm-Based Speech Synthesis", In Proc. of ISCSLP, 2012.

9 [27] Xian-Jun Xia,Zhen-Hua Ling, Chen-Yu Yang, Li-Rong Dai, "Improved Unit Selection Speech Synthesis Method Utilizing Subjective Evaluation Results On Synthetic Speech", in Proc. of ISCSLP, [28] Ming-Qi Cai, Zhen-Hua Ling, and Li-Rong Dai, Target-filtering model based articulatory movement prediction for articulatory control of HMM-based speech synthesis, in Proc. of the 11th International Conference on Signal Processing, [29] Zhen-Hua Ling, Xian-Jun Xia, Yang Song, Chen-Yu Yang, Ling-Hui Chen, and Li-Rong Dai "The USTC System for Blizzard Challenge 2012", in Proc. of Blizzard Challenge workshop, (paper) [30] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, Vowel Creation by Articulatory Control in HMM-based Parametric Speech Synthesis, in Proc. of Interspeech (paper) (demo) [31] Xiang Yin, Zhen-Hua Ling, Ming Lei, Li-Rong Dai, Considering Global Variance of the Log Power Spectrum Derived from Mel-Cepstrum in HMM-based Parametric Speech Synthesis, in Proc. of Interspeech (paper) [32] Ling-Hui Chen, Chen-Yu Yang, Zhen-Hua Ling, Yuan Jiang, Li-Rong Dai, Yu Hu, and Ren-Hua Wang, The USTC system for Blizzard Challenge 2011, in Proc. of Blizzard Challenge workshop, [33] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, Feature-Space Transform Tying in Unified Acoustic-Articulatory Modelling for Articulatory Control of HMM-based Speech Synthesis, in Proc. of Interspeech, pp , [34] Ling-Hui Chen, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, Li-Rong Dai, Estimation of Window Coefficients for Dynamic Feature Extraction for HMM based Speech Synthesis, in Proc. of Interspeech, pp , [35] Ming Lei, Junichi Yamagishi, Korin Richmond, Zhen-Hua Ling, Simon King, Li-Rong Dai, Formant-controlled HMM-based Speech Synthesis, in Proc. of Interspeech, pp , [36] Heng Lu, Zhen-Hua Ling, Li-Rong Dai, Ren-Hua Wang, Building HMM based Unit-Selection Speech Synthesis System Using Synthetic Speech Naturalness Evaluation Score, in Proc. of ICASSP, pp , [37] Ming Lei, Zhen-Hua Ling, Li-Rong Dai, Preserve Ordering Property of Generated LSPs for Minimum Generation Error Training in HMM-based Speech Synthesis, in Proc. of ICASSP, pp , [38] Ling-Hui Chen, Zhen-Hua Ling, Li-Rong Dai, Non-Parallel Training for Voice Conversion based on FT-GMM, in Proc. of ICASSP, pp , [39] Zhen-Hua Ling, Zhi-Guo Wang, Li-Rong Dai, Statistical Modeling of Syllable-Level F0 Features for HMM-based Unit Selection Speech Synthesis, in Proc. of ISCSLP, pp , [40] Ling-Hui Chen, Zhen-Hua Ling, Wu Guo, Li-Rong Dai, GMM-based Voice Conversion with Explicit Modelling on Feature Transform, in Proc. of ISCSLP, pp , [41] Chen-Yu Yang, Zhen-Hua Ling, Heng Lu, Wu Guo, Li-Rong Dai, Automatic Phrase Boundary Labeling for Mandarin TTS Corpus Using Context-Dependent HMM, in Proc. of ISCSLP 2010, pp

10 [42] Tian-Yi Zhao, Zhen-Hua Ling, Ming Lei, Li-Rong Dai, Qing-Feng Liu, Minimum Generation Error Training for HMM-based Prediction of Articulatory Movements, in Proc. of ISCSLP, pp , [43] Ming Lei, Yi-Jian Wu, Zhen-Hua Ling, Li-Rong Dai, Investigation of Prosodic F0 Layers in Hierarchical F0 Modeling for HMM-based Speech Synthesis, in Proc. of International Conference on Signal Processing, pp , [44] Zhen-Hua Ling, Yu Hu, and Li-Rong Dai, Global Variance Modeling on the Log Power Spectrum of LSPs for HMM-based Speech Synthesis, in Proc. of Interspeech, pp , [45] Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi, HMM-based Text-to-Articulatoryovement Prediction and Analysis of Critical Articulators, in Proc. of Interspeech, pp , [46] Heng Lu, Zhen-Hua Ling, Si Wei, Li-Rong Dai, and Ren-Hua Wang, Automatic Error Detection for Unit Selection Speech Synthesis Using Log Likelihood Ratio based SVM Classifier, in Proc. of Interspeech, pp , [47] Ming Lei, Yi-Jian Wu, Frank K. Soong, Zhen-Hua Ling, and Li-Rong Dai, A Hierarchical F0 Modeling Method for HMM-based Speech Synthesis, in Proc. of Interspeech, pp , [48] Yuan Jiang, Zhen-Hua Ling, Ming Lei, Cheng-Cheng Wang, Heng Lu, Yu Hu, Li-Rong Dai, Ren-Hua Wang, The USTC system for Blizzard Challenge 2010, in Proc. of Blizzard Challenge workshop, [49] Ming Lei, Zhen-Hua Ling, and Li-Rong Dai, Minimum generation error training with weighted Euclidean distance on LSP for HMM-based speech synthesis, in Proc. of ICASSP, pp , [50] Cheng-Cheng Wang, Zhen-Hua Ling, and Li-Rong Dai, Asynchronous F0 and spectrum modeling for HMM-based speech synthesis, in Proc. of Interspeech, pp , [51] Heng Lu, Zhen-Hua Ling, Ming Lei, Cheng-Cheng Wang, Huan-Huan Zhao, Ling-Hui Chen, Yu Hu, Li-Rong Dai, and Ren-Hua Wang, The USTC system for Blizzard Challenge 2009, in Proc. of Blizzard Challenge workshop, [52] Long Qin, Yi-Jian Wu, Zhen-Hua Ling, and Ren-Hua Wang, Model adaptation for HMM-based speech synthesis under minimum generation error criterion, in Proc. of IEEE International Symposium on Multimedia, pp , [53] Zhen-Hua Ling, Wei Zhang, and Ren-Hua Wang, Cross-stream dependency modeling for HMM-based speech synthesis, in Proc. of ISCSLP, pp. 5-8, [54] Chen-Cheng Wang, Zhen-Hua Ling, Bu-Fan Zhang, and Li-Rong Dai, Multi-layer F0 modeling for HMM-based speech synthesis, in Proc. of ISCSLP, pp , [55] Heng Lu, Zhen-Hua Ling, Si Wei, Yu Hu, Li-Rong Dai, and Ren-Hua Wang, Heteronym verification for Mandarin speech synthesis, in Proc. of ISCSLP, pp , [56] Wei Zhang, Zhen-Hua Ling, and Li-Rong Dai, Constructing scalable TTS system based on corpus approach, in Proc. of IEEE International Conference on Cybernetics and Intelligent Systems, pp , 2008.

11 [57] Zhen-Hua Ling, Heng Lu, Guo-Ping Hu, Li-Rong Dai, and Ren-Hua Wang, The USTC entry for Blizzard Challenge 2008, in Proc. of Blizzard Challenge workshop, [58] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, and Ren-Hua Wang, Articulatory control of HMM-based parametric speech synthesis driven by phonetic knowledge, in Proc. of Interspeech, pp , [59] Junichi Yamagishi, Zhen-Hua Ling, and Simon King, Robustness of HMM-based speech synthesis, in Proc. of Interspeech, pp , [60] Zhen-Hua Ling, and Ren-Hua Wang, Minimum unit selection error training for HMM-based unit selection speech synthesis system, in Proc. of ICASSP, pp , [61] Long Qin, Yi-Jian Wu, Zhen-Hua Ling, Ren-Hua Wang, and Li-Rong Dai, Minimum generation error linear regression based model adaptation for HMM-based speech synthesis, in Proc. of ICASSP, pp , [62] Zhen-Hua Ling, Long Qin, Heng Lu, Yu Gao, Li-Rong Dai, Ren-Hua Wang, Yuan Jiang, Zhi-Wei Zhao, Jin-Hui Yang, Jie Chen, and Guo-Ping Hu, The USTC and iflytek speech synthesis systems for Blizzard Challenge 2007, in Proc. of Blizzard Challenge workshop, [63] Zhen-Hua Ling, and Ren-Hua Wang, HMM-based unit selection combining Kullback-Leibler divergence with likelihood criterion, in Proc. of ICASSP, pp , [64] Long Qin, Zhen-Hua Ling, Yi-Jian Wu, Bu-Fan Zhang, and Ren-Hua Wang, HMM-based emotional speech synthesis using average emotion model, in Proc. of International Symposium on Chinese Spoken Language Processing (ISCSLP), pp , [65] Bu-Fan Zhang, Zhen-Hua Ling, Long Qin, and Renhua Wang, Applying SFC model for Chinese expressive speech synthesis, in Proc. of ISCSLP, [66] Zhen-Hua Ling, Yi-Jian Wu, Yu-Ping Wang, Long Qin, and Ren-Hua Wang, USTC system for Blizzard Challenge an improved HMM-based speech synthesis method, in Proc. of Blizzard Challenge workshop, [67] Zhen-Hua Ling, and Ren-Hua Wang, HMM-based unit selection using frame sized speech segments, in Proc. of Interspeech, pp , [68] Long Qin, Yi-Jian Wu, Zhen-Hua Ling, and Ren-Hua Wang, Improving the performance of HMM-based voice conversion using context clustering decision tree and appropriate regression matrix format, in Proc. of Interspeech, pp , [69] Zhen-Hua Ling, Yu Hu, and Ren-Hua Wang, A novel source analysis method by matching spectral characters of LF model with STRAIGHT spectrum, in Proc. of the First International Conference on Affective Computing & Intelligent Interaction (ACII), Lecture Notes in Computer Science, vol. 3784, pp , [70] Yu-Ping Wang, Zhen-Hua Ling, and Ren-Hua Wang, Emotional speech synthesis based on improved codebook mapping voice conversion, in Proc. of the ACII, Lecture Notes in Computer Science, vol. 3784, pp , [71] Long Qin, Gao-Peng Chen, Zhen-Hua Ling, and Li-Rong Dai, An improved spectral and prosodic transformation method in STRAIGHT-based voice conversion, in Proc. of ICASSP, vol. 1, pp , 2005.

12 [72] Zhen-Hua Ling, Yu-Ping Wang, Yu Hu, and Ren-Hua Wang, Modeling glottal effect on the spectral envelop of STRAIGHT using mixture of Gaussians, in Proc. of ISCSLP, pp , [73] Zhen-Hua Ling, Yu Hu, Zhi-Wei Shuang, and Ren-Hua Wang, Compression of speech database by feature separation and pattern clustering using STRAIGHT, in Proc. of Interspeech, pp , [74] Zhi-Wei Shuang, Zi-Xiang Wang, Zhen-Hua Ling, and Renhua Wang, A novel voice conversion system based on codebook mapping with phoneme-tied weighting, in Proc. of Interspeech, pp , [75] Zhen-Hua Ling, Yu Hu, Zhi-Wei Shuang, and Ren-Hua Wang, Decision tree based unit pre-selection in Mandarin Chinese synthesis, in Proc. of ISCSLP, [76] Zhi-Wei Shuang, Yu Hu, Zhen-Hua Ling, and Ren-Hua Wang, A miniature Chinese TTS system based on tailored corpus, in Proc. of ICSLP, pp , 国内会议论文 [1] 江源, 朱双华, 凌震华, 戴礼荣, 基于 HMM 的单元挑选语音合成中的改进方法研究, 第 11 届全国人机语音通信会议,2011. [2] Zhen-Hua Ling, Yu Hu, An experimental study on the similarity performance of HMM-based parametric speech synthesis, in Proc. of the 10th National Conference on Man-Machine Speech Communication, [3] 赵欢欢, 凌震华, 秦龙, 王仁华, 戴礼荣, 基于 EigenVoice 模型自适应的语音合成话者转换方法, 第九届全国人机语言通讯学术会议, [4] 高羽, 凌震华, 戴礼荣, 王仁华, 一种改进的正弦语音分析合成器, 第九届全国人机语言通讯学术会议, [5] 卢恒, 张巍, 凌震华, 王仁华, 戴礼荣, 基于多高斯建模和挑选的 HMM 语音合成系统, 第九届全国人机语言通讯学术会议, [6] 周斌, 凌震华, 双志伟, 王仁华, 基于逆滤波和 LF 声源建模的语音合成器研究, 第七届全国人机语言通讯学术会议, [7] 王仁华, 胡郁, 李威, 凌震华, 基于决策树的汉语大语料库合成系统, 第六届全国人机语音通讯学术会议论文集,2001.

双语教学之中综上所述, 科大讯飞畅言交互式多媒体教学系统, 围绕语音核心技术的研究与创新, 取得了一系列自主产权并达到国际领先水平的技术成果, 同时获得发明专利 3

双语教学之中综上所述, 科大讯飞畅言交互式多媒体教学系统, 围绕语音核心技术的研究与创新, 取得了一系列自主产权并达到国际领先水平的技术成果, 同时获得发明专利 3 博士后制度实施 30 周年成果展科大讯飞股份有限公司二博士后科研成就胡国平博士在博士后工作站期间承担的项目为畅言交互式多媒体教学系统畅言交互式多媒体教学系统是基于科大讯飞国际领先的中英文合成识别及自动口语评