1.语音信息处理

2.自然语言处理

3.图像处理

4.情感计算

5.人工智能

研究生课程：数字语音信号处理、计算机系统设计、Computer Architecture & Organization（留学生）
本科生课程：计算机组成与结构（院核心）、计算机系统（院核心）、计算机科学概论（校通识平台）、ARM体系结构与编

程（选修）、计算机系统设计（选修）

[1]面向情感计算的智能语音对话系统响应生成.国家自然科学基金,主持. 2021-2024

[2]新能源汽车制造产业集聚区域网络协同制造集成技术研究与应用示范.国家重点研发计划,任务(课题)负责人. 2021-2023

[3]多源涉诉信访智能处置技术研究.国家重点研发计划,课题骨干. 2018-2021

[4]面向语音环境基于情感计算的动态推荐系统模型研究.国家自然科学基金,主持. 2018-2021

[5]新一代汽车中智能语言处理若干关键技术研究.国家自然科学基金,主持. 2012-2015

[6]互联网中图文与版式文件的涉密信息检测系统研制，长沙市科技计划重点项目，主持，2014-2015

[7]基于嵌入式平台的自动语音识别系统前端处理关键技术研究.湖南省自然科学基金重点项目,主持. 2010-2012

[8]嵌入式异构多核体系任务调度机制的研究与实现.湖南省科技计划,主持. 2009-2010

[9]基于数据挖掘技术的语音合成方法研究.湖南省自然科学基金,主持. 2004-2005

[10]工业试验台智能测控系统.湖南省科技计划,主持. 2003-2005

[11]语音合成在嵌入式系统中的应用研究.湖南省科技计划,主持. 2005-2007

[12]嵌入式语音处理算法研究及嵌入式语音系统设计.湖南省财政厅资助项目,主持. 2006-2008

[13]基于无线网络的视音频动态迁移系统开发.湖南省科技计划重点项目,参与. 2010-2012

[14]中国网上教育平台试点工程高教子系统开发.国家发改委重大项目,参与. 2004-2005

[15]湖南麓山云数据科技服务有限公司-湖南大学产学研合作项目.技术服务, 300万元,负责人. 2017-2019

[16]计算机系统组成与体系结构.国家级精品资源共享课程,负责人. 2013

[17]计算机系统组成与体系结构.国家级精品课程,负责人. 2009

[1]物联网若干关键技术及其行业应用.湖南省技术发明二等奖,第四. 2019

[2]新型嵌入式计算机系统结构及其应用.湖南省科技进步二等奖,第五. 2006

[3]WYBT-998无线遥控变频调速控制系统.湖南省科技厅科技进步二等奖,第十. 2000

[4]CB-928长沙北站装卸微机综合管理系统.湖南省科技进步四等奖,第四. 1994

(一) 期刊论文

[1]Zhao Huan, Cao Jie, Xu Mingquan, and Lu Jian.Variational neural decoder for abstractive text summarization. Computer scienceand Information Systems, 2020, 17(2):537-552. JCR三区, SCI四区

[2]Huan Zhao, Tingting Li, Yufeng Xiao and Yu Wang.Improving Multi-Agent Generative Adversarial Nets with Variational LatentRepresentation. Entropy, 2020,22,1055: 1-18. JCR二区, SCI三区

[3]Huan Zhao, Yufeng Xiao, Zixing Zhang. RobustSemisupervised Generative Adversarial Networks for Speech Emotion Recognitionvia Distribution Smoothness. IEEE Access, 2020, 8(6): 106889-106900. JCR一区, SCI二区, EI

[4]Huan Zhao, Song Wang, Xiaolin She, Chenghui Su.Supervised Matrix Factorization Hashing with Quantitative Loss for Image-TextSearch. IEEE Access, 2020, 8(5): 102051-102064. JCR一区, SCI二区, EI

[5]Yufeng xiao, Huan zhao, Tingting Li. LearningClass-aligned and Generalized Domain-invariant Representations for SpeechEmotion Recognition. IEEE Transactions on Emerging Topics in ComputationalIntelligence, 2020, 4(4): 480-489

[6]Shaofang He, Huan Zhao.Automatic SyllableSegmentation Algorithm of Chinese Speech based on MF-DFA. Speech Communication,2017,92(9): 42-51.语音信号处理顶刊，CCF B

[7]Huan Zhao, Shaofang He. Analysis of speech signals'characteristics based on MF-DFA with moving overlapping windows. PhysicaA:Statistical Mechanics and its Applications, 2016, 442(1): 343-349.二区

[8]Huan Zhao, Shaofang He, Zuo Chen, and XixiangZhang. Dual Key Speech Encryption Algorithm Based Underdetermined BSS. TheScientific World Journal, 2014.5.二区

[9]Aboubakar Nasser Samatin Njikam, Huan Zhao. A novelactivation function for Multilayer feed-forward neural networks. AppliedIntelligence, 2016, 45(1): 75–82. CCF C,三区

[10]Huan Zhao, Gangjin Wang, Cheng Xu, Fei Yu. VoiceActivity Detection Method Based on Multi-valued Coarse-graining Lempel-ZivComplexity. Computer Science and Information Systems, 2011, 8(3): 869-888.三区

[11]Zhao Huan, Zhang Xixiang, Li Keqin. A Sentiment ClassificationModel Using Group Characteristics of Writing Style Features. InternationalJournal of Pattern Recognition and Artificial Intelligence, 2017,31(12):1756016(19 pages). CCF C,四区

[12]He Shaofang, Zhao Huan. A Retrieval Algorithm ofEncrypted Speech based on Syllable-level Perceptual Hashing. Computer Scienceand Information System, 2017,14(3):703-718.四区

[13]Huan Zhao, Zhiqiang Lu, Fei Yu,Cheng Xu. A NovelMagnitude-Squared Spectrum Cost Function for Speech Enhancement. Elektronika IrElektrotechnika, 2012, 122(6):11-14.四区

[14]Huan Zhao, Fei Wang, Zuo Chen. A Robust AudioWatermarking Algorithm Based on SVD-DWT. Elektronika Ir Elektrotechnika, 2014,20(1): 75-80.四区

[15]Huan Zhao, Jun Liu, Zuo Chen, Fei Wang. A New SoftMasking Method for Speech Enhancement in Frequency Domain. Elektronika IrElektrotechnika, 2014,20(2): 58-63.四区

[16]赵欢,李仁发,王家琴,张在美.一种综合多层信息的本体概念相似度计算方法研究.通信学报, 2009, 30(6): 135-141. EI

[17]赵欢,王纲金,胡炼,彭秀娟.车载环境下基于样本熵的语音端点检测方法.计算机研究与发展, 2011, 48(3): 471-476. EI

[18]赵欢,谭华. Apriori算法在语音合成应用中的一种改进.湖南大学学报自然科学版, 2004, 31(5): 94-98. EI

[19]赵欢,王纲金,赵丽霞.一种新的对数能量谱熵语音端点检测方法.湖南大学学报自然科学版, 2010, 37(7): 72-77. EI

[20]San Shibing, Zhao Huan. Research on the RegressionAlgorithm Analysis and its Application. Data Science Journal, 2007, 6(SUPPL):S485-S491. EI

[21]Huan Zhao, Xiujuan Peng, Lian Hu, Gangjin Wang, FeiYu, Cheng Xu. An Improved Speech Enhancement Method Based on Teager EnergyOperator and Perceptual Wavelet Packet Decomposition. Journal of Multimedia,2011, 6(3):308-315. EI

[22]Huan Zhao, Lian Hu, Xiujuan Peng, Gangjin Wang, FeiYu, Cheng Xu. An Improving MFCC Features Extraction Based on Fast ICA AlgorithmPlus RASTA Filtering. Journal of Computers, 2011, 6(7): 1477-1484. EI

[23]Huan Zhao, He Liu, Kai Zhao, Yong Yang. RobustSpeech Feature Extraction Using the Hilbert Transform Spectrum EstimationMethod. International Journal of Digital Content Technology and its Applications,2011, 5(12): 85-95. EI

[24]Zhao Huan, Zhao Kai, Liu He, Yu Fei. Improved MFCCfeature extraction combining symmetric ICA algorithm for robust speechrecognition. Journal of Multimedia, 2012,7(1): 74-81. EI

[25]Huan Zhao, Yufeng Xiao. A Novel Robust MFCC ExtractionMethod Using Sample-ISOMAP for Speech Recognition. International Journal ofDigital Content Technology and its Applications, 2012, 6(19): 393-400. EI

[26]Huan Zhao, Yong Yang, Zhiqiang Lu, Yu Fei.Efficient β-order Perceptually Motivated Spectral Amplitude Bayesian EstimatorBased on Chi-distribution for Speech Enhancement. Journal of Computers, 2012,7(11): 2829-2835. EI

[27]Huan Zhao, Wenjie Gan. A New Pitch EstimationMethod Based on AMDF. Journal of Multimedia, 2013, 8(5): 618-625. EI

[28]Zhao huan, Guo shaobin, Liu jun. Use of modifiedgain function with speech presence uncertainty for speech enhancement. Journalof Computational Information Systems, 2014,10(1): 385-393. EI

[29]Rui Zheng, Huan Zhao, Xixiang Zhang. A WordSimilarity Algorithm with Sememe Probability Density Ratio Based on HowNet.International Journal of Hybrid Information Technology, 2015, 8(10): 417-426. EI

[30]Huan Zhao, Jiaolong Wan, Zuo Chen. A noveldummy-based KNN query anonymization method in mobile services. InternationalJournal of Smart Home,2016, 10(6): 137-154. EI

[31]Xixiang Zhang, Huan Zhao. A Long-Term FeatureSelection Based on Heuristic Strategy for Speaker Diarization. Journal ofInformation Hiding and Multimedia Signal Processing, 2017, 8(2): 381-391. EI

[32]Zhang Xixiang, Zhao Huan. Cold-start RecommendationBased on Speech Personality Traits. Journal of Computational and TheoreticalNanoscience. 2017,14(3):1314-1323. EI

[33]Zhao Huan, Tan Biao, Zhang Xixiang. Improved SpeechEmotion Recognition using Attributes Evaluation and Multi-layer Perceptron.Journal of Computational and Theoretical Nanoscience. 2017, 14(8): 3983-3987.EI

(二) 会议论文

[1]Huan Zhao, Yu Wang, Tingting Li and YuqingZhao. An Asymmetric Two-sided PenaltyTerm for CT-GAN. In Proc of MMM 2021(The 27st International Conference onMultiMedia Modeling), 22-24 June 2021, Czech Republic, Prague. CCF C类会议. (Accepted)

[2]Huan Zhao, Xiaolin She, Song Wang and Kaili Ma.Fast Discrete Matrix Factorization Hashing for Large-Scale Cross-ModalRetrieval. In Proc of MMM 2021(The 27st International Conference on MultiMediaModeling), 22-24 June 2021, Czech Republic, Prague. CCF C类会议. (Accepted)

[3]Huan Zhao*, Mingquan Xu, Jie Cao. Pre-trainedLanguage Model Transfer on Chinese Named Entity Recognition. HPCC-SmartCity-DSS2019(21st IEEE International Conference on High Performance Computing andCommunications/17th IEEE International Conference on Smart City/5th IEEEInternational Conference on Data Science and Systems), 10-12 August 2019,Zhangjiajie, China: 2150-2155. CCF C类会议.

[4]Huan Zhao, Yufeng xiao, Jing Han, Zixing Zhang.Compact Convolutional recurrent Neural Networks Via Binarization for SpeechEmotion Recognition. ICASSP 2019, 12-17 May, 2019. Brighton, UK.ICASSP:6690-6694.语音信号处理顶会，CCF B

[5]Huan Zhao, Li Meng. Centroid-based KNN Query inMobile Service of LBS. NOMS 2018, 23-27 April, 2018. Taipei, Taiwan. NOMS 2018:1-6. CCF C

[6]Huan Zhao, Zeying Yang, Zuo Chen, and XixiangZhang. Automatic Chinese Personality Recognition Based on Prosodic Features.MMM 2015, 5-7 January, 2015, Sydney, Australia. Part I, LNCS 8935:180–190,2015. CCF C

[7]Huan Zhao, Qian Zhang, Liang Zhang and Yan Wang. ANovel Sensor Deployment Approach Using Fruit Fly Optimization Algorithm inWireless Sensor Networks. IEEE Trust Com 2015, 20-22 August 2015. Helsinki,Finland. 2015 IEEE Trustcom/BigDataSE/ISPA(Volume 1): 1292-1297. CCF C

[8]Huan Zhao, Chaoming Hu, Rui Zheng and Bin Lv. Studyon the Coverage of Adaptive Wireless Sensor Network Based on Trust. IEEETrustCom 2015, 20-22August 2015. Helsinki, Finland. IEEE Trustcom/BigDataSE/ISPA(Volume 1):1312-1317. CCF C

[9]Huan Zhao, Xixiang Zhang. A Mobile Security-relatedBehavior Prevention Model Based on Speech Personality Traits. IEEE TrustCom2016, 23-26 August2016. Tianjin, China. 2016 IEEE Trustcom/BigDataSE/ISPA:1803-1810. CCF C

（一） 发明专利

[1]赵欢,王松,陈佐,谭彪.一种融合特征评估和多层感知器的语音情感识别方法, 2017年.发明专利,授权,专利号：201710607479.9.

[2]赵欢,李婷婷,李祎颖.一种基于主体增强的文本摘要生成方法, 2020年.发明专利,实审中.

[3]赵欢,李博,李祎颖.基于复制机制和变分神经推理的增强性文本摘要生成方法, 2020年.发明专利,实审中.

[4]赵欢,周晓晓,肖宇锋,陈佐.基于DIS-NV特征的语音情感识别方法, 2017年.发明专利，实审中.

[5]赵欢,张希翔,谭彪.基于即时语音内容检测的推荐方法及系统, 2015年.发明专利,授权,专利号ZL 2015 1 0662383.3.

[6]赵欢,郑睿,陈佐,杨泽英,张谦.一种用于移动平台的无线语音控制方法及系统, 2014年.发明专利,授权,专利号ZL 2014 1 0285216.7.

[7]赵欢,郑睿,陈佐,张希翔,杨泽英.一种声音模仿方法及装置, 2013年.发明专利,授权,专利号ZL 2013 1 0423715.3.

[8]赵欢,王飞,陈佐,干文洁.具有语音控制和哼唱检索功能的多媒体播放方法及装置, 2013年.发明专利,授权,专利号ZL 2013 1 0298771.9.

(二) 实用新型专利

[1]赵欢,王飞,陈佐,干文洁.具有语音控制和哼唱检索功能的多媒体播放装置,实用新型专利,授权,专利号: ZL 2013 2 0422658.2.

[2]赵欢,冯璐,陈佐,王飞.具有语音及文本输出选择功能的移动通信装置,实用新型专利,授权,专利号ZL 2013 2 0461679.5.

[3]赵欢,陈佐.面向实时音视频流的字幕叠加系统.实用新型专利,授权,专利号: ZL 2011 2 0558388.9.

[4]徐成,李仁发,刘彦,秦云川,罗正钦,黄春毅,彭蔓蔓,吴蓉晖,赵欢.无线多媒体实时学习系统与方法,实用新型专利,授权(受理号200610032349.9,公开号CN101155089).

(三) 软件著作权

[1]赵欢(湖南大学).文本摘要自动生成软件.计算机软件著作权,登记号：2020SR0391470.

[2]赵欢(湖南大学).基于Seq2Seq框架的闲聊对话系统,V1.0,2019.12.计算机软件著作权,登记号：2019R11L1950501.

[3]赵欢(湖南大学).基于微博话题的情感多分类系统V1.0, 2018.11.计算机软件著作权,登记号：2019SR0216837.

[4]赵欢(湖南大学).基于信任关系的协同过滤推荐系统V1.0, 2018.1.计算机软件著作权,登记号：2018SR329655.

[5]赵欢(湖南大学).基于语音的人格特征评估系统, 2016.3.计算机软件著作权,登记号：2016SR108509.

[6]彭飞(湖南大学).互联网中图文与版式文件的涉密信息检测系统,2015.12.计算机软件著作权,登记号：2016SR031982.

[7]赵欢(湖南大学).支持视音频动态迁移的媒体播放器软件. 2010.9.计算机软件著作权,登记号：2011SR007494.