肖仲喆
职称: 讲师
院部/部门: 光电信息科学与工程学院

电子邮箱: xiaozhongzhe@suda.edu.cn

联系电话: 13913520247

办公地点: 物理科技楼407

个人简介

2010.9 - 今     苏州大学物理科学与技术学院(现物理与光电·能源学部),讲师
2014.3 - 2014.6 美国斯坦福大学(Stanford University),访问学者

2004.9 - 2008.1    法国里昂中央理工大学(Ecole Centrale de Lyon),博士研究生,
              2009年获得博士学位
2000.9 - 2003.7    清华大学电子工程系电路与系统专业,硕士研究生,获工学硕士学位
1996.9 - 2000.7    清华大学电子工程系无线电技术与信息系统专业,本科,获工学学士学位

研究方向

1. 情感语音研究
    研究语音与情感的关系,包括语音情感模型,语音参数,语音情感识别模型,以及语音情感合成/转换模型等。
2. 音乐计算
    以音乐情绪表达为核心的音乐计算,通过旋律、节奏等音乐特征以及各种感知特征进行音乐情绪识别。
    近期以中国民族乐器古筝的情绪表达为主要研究对象。

科学研究

科研团队

论文成果

国际学术期刊论文:

·         Zhongzhe Xiao, Emmanuel Dellandréa,Weibei Dou, Liming Chen, Classification of Emotional Speech Based on anAutomatically Elaborated Hierarchical Classifier, ISRN signal processing, vol.2011, Article ID 753819, 15 pages, 2011. doi:10.5402/2011/753819.

·         Zhongzhe Xiao, Emmanuel Dellandréa,Weibei Dou, Liming Chen, Multi-stage classification of emotional speechmotivated by a dimensional emotion model, Multimedia Tools and Applications,Volume 46, Issue 1 (2010), Page 119-145.

 

国际会议论文:

·         Zhongzhe Xiao, Di Wu,Xiaojun Zhang, Zhi Tao, Speech Emotion Recognition Cross Language Families:Mandarin vs. Western Languages, in the Proceedings of the 2016 IEEEInternational Conference on Progress in Informatics and Computing (PIC2016),December 23-25, 2016, Shanghai, China, p253-257.

·         Zhongzhe Xiao, Di Wu,Xiaojun Zhang, Zhi Tao, A Cross-Corpus Recognition of Emotional Speech,Proceedings of 2016 9th International Symposium on Computational Intelligenceand Design (ISCID 2016), vol 2, p42-46, Dec. 10-11, 2016 in Hangzhou,China

·         Di Wu,Zhi Tao, Yuanbo Wu, Cheng Shen, Zhongzhe Xiao, Xiaojun Zhang, Di Wu,Heming Zhao, Speech endpoint detection in noisy environment using SpectrogramBoundary Factor, 2016 9th International Congress on Image and SignalProcessing, BioMedical Engineering and Informatics (CISP-BMEI), p964-968,2016.10.15-17, Datong, P. R. China.

·         Di Wu,Heming Zhao, Zhe Feng, Liyuan Chen, Zhongzhe Xiao, Xiaojun Zhang, ZhiTao, Perception auditory factor for speaker recognition in noisy environment,2016 12th International Conference on Natural Computation, Fuzzy Systems andKnowledge Discovery (ICNC-FSKD), p1916-1920, 2016.8.13-15, Changsha, P. R.China.

·         Zhongzhe Xiao, Di Wu,Xiaojun Zhang, Zhi Tao, Music Mood Tracking Based on HCS, Proceedings 2012 IEEE11th International Conference on Signal Processing, p. 1171-1175, October 21 -25, 2012, Beijing,

·         Bingjie Li, Zhongzhe Xiao,Yan Shen, Qiang Zhou, Zhi Tao*, Emotional Speech Conversion Based onSpectrum-prosody Dual Transformation, Proceedings 2012 IEEE 11th InternationalConference on Signal Processing, p. 531-535, October 21 - 25, 2012, Beijing

·         Huanzhang Fu, Zhongzhe Xiao,Emmanuel Dellandréa, Liming Chen, Image Categorization using ESFS: a newembedded Feature Selection Method Based on Evidence Theory, Intl. conf.Advanced Concepts for Intelligent Vision Systems (ACIVS 2009), Bordeaux,France,  September 2009

·         Zhongzhe Xiao, EmmanuelDellandréa, Weibei Dou, and Liming Chen, What is the Best Segment Duration forMusic Mood Analysis? Sixth International Workshop on Content-Based MultimediaIndexing (CBMI 2008), June 2008, London, UK.

·         Zhongzhe Xiao, EmmanuelDellandréa, Weibei Dou, and Liming Chen, Ambiguous classification of emotionalspeech, International Workshop on EMOTION - satellite of InternationalConference on Language Resources and Evaluation (LREC), 2008.

·         Zhongzhe Xiao, EmmanuelDellandréa, Weibei Dou, and Liming Chen, Automatic Hierarchical Classificationof Emotional Speech,Ninth IEEE International Symposium on Multimedia Workshops(ISMW 2007), Taichung, Taiwan. pp. 291-296.

·         Zhongzhe Xiao, EmmanuelDellandréa, Weibei Dou, and Liming Chen, Two-stage Classification of EmotionalSpeech, International Conference on Digital Telecommunications (ICDT'06), p.32-37, August 29 - 31, 2006, Cap Esterel, C?te d’Azur, France.

·         Zhongzhe Xiao, EmmanuelDellandréa, Weibei Dou, and Liming Chen, Features extraction and selection foremotional speech classification, IEEE Conference on Advanced Video and SignalBased Surveillance, 2005. AVSS 2005, p411 - 416,Como, Italy

·         Zhongzhe Xiao, ZaiwangDong, Improved GIB synchronization method for OFDM systems, 10th InternationalConference on Telecommunications, 2003. ICT 2003, p1417 - 1421,vol.2

国内期刊论文:

·         沈燕,肖仲喆,李冰洁,周孝进,周强,陶智,采用GW-MFCC模型空间参数的语音情感识别. 计算机工程与应用,201551(10):219-222+226.

·         黄程韦,吴迪,张晓俊,肖仲喆,许宜申,季晶晶,陶智,赵力,基于级联投影高斯混合模型的语音与心电情绪识别. 东南大学学报:英文版,2015,(3: 320-326.

·         吴迪,赵鹤鸣,陶智,张晓俊,肖仲喆,许宜申,低信噪比下采用感知语谱结构边界参数的语音端点检测算法,声学学报,2014(3): 392-399.

·         张晓俊,陶智,吴迪,肖仲喆,赵鹤鸣,采用多特征组合优化的语音特征参数研究,通信技术,201245(12): 98-100.

荣誉奖励

课程教学

主要主讲过的课程:

1. 数字信号处理
2. 信号与线性系统
3. 微弱信号检测
4. 专业英语
5. 电路与电子学
6. 光电检测技术

招生信息