当前位置:首页 > 师资力量
  • 姓名:宋鹏
  • 职务:
  • 职称:讲师    
  • 所在院系:计算机系
  • 最后学位:博士
  • 最后学历:博士研究生
  • 最后毕业院校:东南大学
  • 专业方向:语音信号处理、模式识别、机器学习
  • 联系方式:pengsongseu@gmail.com
个人简介

教育经历:

2011/02 2014/06:   东南大学,         信息与通信工程,  工学博士    

2006/09 2009/03:   东南大学,         信号与信息处理,  工学硕士    

2002/09 2006/06:   山东科技大学,     电子信息工程,   工学学士

工作经历:

2014/07–至      :     烟台大学,                                        教师             

2009/032011/01:    摩托罗拉(中国)软件研发中心,        软件工程师      

2007/122008/05:    微软亚洲研究院,                           研究实习生     

目前研究兴趣:

语音信号处理(语音情感识别、语音转换、语音增强、说话人识别等)

机器学习(迁移学习、子空间学习等)

城市计算(交通大数据等)

计算机视觉(面部表情识别等)

学术活动:

目前为IEEE(SPS)会员、IEICE会员、CCF会员。同时担任IEEE Trans. on Affective Computing, Speech Communication, Pattern Recognition Letters, IEEE Signal Processing Letters等10余个国际国内期刊审稿人。

目前主持的科研项目:

1) 国家自然科学基金,面向多语种语音数据的自适应情感识别算法研究(61703360), 2018.01-2020.12

2) 山东省自然科学基金,跨语言非特定人语音情感识别关键技术研究 (ZR2014FQ016), 2014.12-2017.12

3) 教育部重点实验室开放基金, 面向多语种语音的情感识别(CDLS-2017--02), 2017.01-2018.12

4) 教育部重点实验室开放基金,  面向儿童的实用语音情感识别关键技术研究 (CDLS-2015-04), 2015.01-2016.12(结题,被评为优秀

主讲课程:
C/C++程序设计、计算机应用基础
主要科研成果

期刊论文

  1. Peng Song. Transfer Linear Subspace Learning for Cross-corpus Speech Emotion Recognition. IEEE Transactions on Affective Computing. 2017. DOI: 10.1109/TAFFC.2017.2705696 (情感计算领域顶级期刊,SCI,IF:3.149,  JCR一区)
  2. Zhenbin Du, Tsung-Chih Lin, Peng Song. Fuzzy Mixed H-2/H-infinity Sampled-Data Control System. Control Engineering and Applied Informatics.  2017, 19(3):13-21.  (SCI)
  3. Shifeng Ou, Peng Song, Ying Gao. Phase-Sensitive Decision-Directed SNR Estimator for Single-Channel Speech Enhancement. International Journal of Pattern Recognition and Artificial Intelligence. 2017, 31(8): 1758003-1~1758003-16 (SCI, CCF C类, IF:0.994)
  4. Peng Song, Shifeng Ou, Zhenbin Du, et al. Learning corpus-invariant discriminant feature representations for speech emotion recognition. IEICE TRANSACTIONS on Information and systems. 2017, E100-D(5): 1136-1139. (SCI,  IF:0.411)
  5. 欧世峰, 刘伟, 宋鹏, 赵晓晖. 采用复高斯分布模型的两步噪声幅度谱估计算法.  信号处理. 2017, 33(7): 918-926.
  6. 张昕然, 巨晓正, 宋鹏, 查诚, 赵力. 用于跨库语音情感识别的DBN特征融合方法. 信号处理,  2017, 33 (5): 649-660.
  7. Peng Song, Wenming Zheng, Shifeng Ou, et al. Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization. Speech Communication. 2016, 83:34-41. (语音领域顶级期刊, CCF B类,SCI,  IF: 1.768, JCR二区)
  8. Peng Song, Shifeng Ou, Xinran Zhang, et al. Transfer Semi-Supervised Non-Negative Matrix Factorization for Speech Emotion Recognition, IEICE TRANSACTIONS on Information and Systems, 2016, E99-D(10):2647-2650. (SCI,  IF:0.411)
  9. 宋鹏, 郑文明, 赵力. 基于特征迁移学习方法的跨库语音情感识别, 清华大学学报(自然科学版), 2016, 56 (11): 1179-1183. (EI)
  10. 张昕然, 宋鹏, 查诚 et al. 用于跨库语音情感识别的时频原子听觉注意模型, 东南大学学报英文版, 2016, 32 (4): 402-407. (EI)
  11. 宋鹏, 金赟, 查诚, 等. 基于稀疏特征迁移的语音情感识别[J]. 数据采集与处理, 2016, 31(2): 325-330.
  12.  Peng Song, Wenming Zheng, Xinran Zhang, et al. A Novel Iterative Speaker Model Alignment Method from Non-Parallel Speech for Voice Conversion IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences, 2015, E98A(10): 2178-2181. (SCI, IF:0.274)
  13. Peng Song, Wenming Zheng, Ruiyu Liang, Speech Emotion Recognition Based on Sparse Transfer Learning Method. IEICE TRANSACTIONS on Information and Systems, 2015, E98-D(7):1409–1412. (SCI,  IF:0.411)
  14. Peng Song, Yun Jin, Cheng Zha, et al. Speech emotion recognition method based on hidden factor analysis. Electronics Letters. 2015, 51(1):112-114. (SCI, IF: 1.155, JCR三区)
  15. 金赟, 宋鹏, 郑文明, 赵力. 半监督判别分析的跨库语音情感识别. 声学学报, 2015, 40(1): 20-27.  (EI)
  16. Peng Song, Yun Jin, Li Zhao, et al. Speech emotion recognition using transfer learning. IEICE TRANSACTIONS on Information and Systems, 2014, E97-D(9):2530–2532. (SCI, IF:0.411)
  17. Hao Wang, Xinmin Cheng, Peng Song, et al. An extrapolated impulse response filter design with sparse coefficients based on a novel linear approximation matrix. Circuits, Systems, and Signal Processing.,2014, 1-27. (SCI,  IF: 1.694, JCR二区)
  18. 宋鹏,王浩,赵力. 基于混合Gauss归一化的语音转换算法[J], 清华大学学报(自然科学版), 2013, 53(6):757-761 (EI)
  19. 宋鹏,王浩,赵力. 采用模型自适应的语音转换方法. 信号处理, 2013, 29(10): 1294-1299.
  20. Yun Jin, Peng Song, Wenming Zheng, et al. Speaker independent speech emotion recognition based on two-layer multiple kernel learning[J], IEICE TRANSACTIONS on Information and Systems. 2013, 96(10): 2286-2289. (SCI,  IF:0.411)
  21. Peng Song, Li Zhao, Yongqiang Bao. Spectral mapping using kernel principal components regression for voice conversion. Archives of Acoustics, 2013, 38(1):39–45. (SCI, IF:0.816, JCR三区)
  22. Yun Jin, Peng Song, Wenming Zheng, et al. A novel feature fusion method for speech emotion recognition based on multiple kernel learning[J], Journal of Southeast University (English Edition). 2013, 29(2): 129-133. (EI)
  23. Peng Song, Yun Jin, Li Zhao, et al. Voice conversion based on hybrid SVR and GMM. Archives of Acoustics, 2012, 37(2):143–149. (SCI, IF:0.816, JCR三区)
  24. Peng Song, Li Zhao, Cairong Zou. Emotional speaker recognition based on prosody transformation[J], Journal of Southeast University (English Edtiion), 2012, 28(2):140–144. (EI)
  25. Peng Song, Yun Jin, Yongqiang Bao, et al. Efficient fundamental frequency transformation for voice conversion, Journal of Southeast University (English Edition), 2012, 27(4):357–360.(EI)
  26. Peng Song, Yongqiang Bao, Li Zhao, et al. Voice conversion using support vector regression. Electronics Letters, 2011, 47(18):1045–1046. (SCI, IF: 1.155, JCR三区) 

会议论文

  1. 宋鹏, 郑文明, 赵力. 基于子空间学习和特征选择融合的语音情感识别.  全国人机语音通讯学术会议(NCMMSC). Lian yungang, China,2017. (oral, 清华大学学报(自然科学版)录用, EI)
  2. 赵冠哲, 齐建鹏, 于彦伟, 刘兆伟, 宋鹏. 移动社交网络异常签到在线检测算法. 中国计算机学会人工智能会议(CCFAI ).  Kunming, China, 2017. (录用,智能系统学报)
  3. Ruoshan Lan, Yanwei Yu, Lei Cao, Peng Song, Yingjie Wang. Discovering Moving Object Evolving Groups from Massive Trajectory Streams. International Conference on Mobile Data Management (MDM). Daejeon, South Korea, 2017. 256-265 (EI,oral, CCF C 类)
  4. Peng Song, Shifeng Ou, Wenming Zheng, et al. Speech Emotion Recognition Using Transfer Non-negative Matrix Factorization. International Conference on Acoustics, Speech and Signal Processing (ICASSP),Shanghai, China, 2016. 5180-5184. (EI, oral, 语音领域顶级国际会议,CCF B类)
  5. Shifeng Ou, Wei Liu, Peng Song, et al. Speech enhancement using a geometric decision-directed approach. International Conference on Audio, Language and Image Processing (ICALIP). Shanghai, China, 2016. 674-678. (EI) 
  6. Peng Song, Xinran Zhang, Shifeng Ou, et al. Cross-corpus speech emotion recognition using transfer semi-supervised discriminant analysis. The 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China, 2016.(EI, oral, 语音领域重要国际会议)
  7. 于彦伟,齐建鹏,宋鹏, 张永刚. 面向不确定移动对象的连续K近邻查询算法. 第五届中国数据挖掘会议 (CCDM),Guilin, China, 2016. (oral, 《模式识别与人工智能》)
  8. Peng Song, Wenming Zheng, Jingjing Liu, et al. A Novel Speech Emotion Recognition Method via Transfer PCA and Sparse Coding. Chinese Conference on Biometric Recognition (CCBR), Tianjin, China, 9428: 393–400, 2015 (EI, oral)
  9. 宋鹏,郑文明,赵力. 基于特征迁移学习方法的跨库语音情感识别. National Conference on Man-Machine Speech Communication ( NCMMSC) , Tianjin, China, 2015.(oral)
  10. Peng Song, Yun Jin, Wenming Zheng, et al. Text-independent voice conversion using speaker model alignment method from non-parallel speech. In: INTERSPEECH, Singapore. 2308-2312, 2014. (EI, oral, 语音领域顶级国际会议, CCF C类)
  11. Yun Jin, Peng Song, Wenming Zheng, et al. A feature selection and feature fusion combination method for speaker-independent speech emotion recognition. In:  International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2014, Florence, Italy. 4841-4845.(EI, 语音领域顶级国际会议, CCF B类)
  12. Peng Song, Wenming Zheng, Li Zhao. Non-parallel training for voice conversion based on adaptation method. In:  International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2013, Vancovour, Canada. 6905-6909. (EI, oral, 语音领域顶级国际会议,,CCF B类)
  13. 宋鹏,王浩,赵力. 基于混合Gauss 归一化的语音转换方法. National Conference on Man-Machine Speech Communication ( NCMMSC) , Guiyang, China, 2013. (oral)
  14. Peng Song, Yongqiang Bao, Li Zhao. Voice conversion using improved spectral and F0 transformation methods. In: Chinese Conference on Pattern Recognition (CCPR). 2012, Beijing, China, 589–596. (EI)

授权专利

  1. 宋鹏,赵力,“基于自适应算法的非对称语料库条件下的语音转换方法”(专利号: CN201310146293.X)
  2. 宋鹏,赵力,金赟. “基于说话人模型对齐的非对称语音库条件下的语音转换方法”(专利号:CN201410399475.2)

录用及近期投稿

  1. Shifeng Ou, Peng Song, Ying Gao. Soft Decision based Gaussian-Laplacian combination model for noisy speech enhancement. Chinese Journal of Electronics. (In press, SCI)
  2. Shifeng Ou, Peng Song. Ying Gao, Laplacian speech model and soft decision based MMSE estimator for noise power spectral density in speech enhancement. Chinese Journal of Electronics. (In press, SCI)
  3. 齐建鹏, 于彦伟, 王创存, 曹磊, 宋鹏. 基于多核多线程的不确定移动对象连续k近邻查询算法. 浙江大学学报(工学版). (In press, EI)
  4. Feature Selection Based Transfer Subspace Learning for Speech Emotion Recognition. Submitted to IEEE Transactions on Affective Computing. (Under review)
  5. Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition. Submitted to ICASSP 2018. (Under review)
  6. A Joint Convolutional Bidirectional LSTM Framework for Facial Expression Recognition. Submitted to IEICE TRANSACTIONS on Information and Systems. (Conditional Accept)
主要教学成果
  1. 2017年国家级大学生创新创业训练计划项目:“基于机器学习的城市交通动态预测” (201711066005)
  2. ASC17世界大学生超级计算机比赛二等奖 
  3. ASC16世界大学生超级计算机比赛Prize of Excellence (二等奖
  4. 烟台大学2017年大学生创新创业训练计划一类项目:“基于机器学习的城市交通动态预测”



指导研究生情况

联系我们

地址:中国山东省烟台市莱山区清泉路30号

邮政编码:264005 电话: 0535-6902601

E-mail: jsjb@ytu.edu.cn

学院官方微信

学院官方微信
Copyright (C) 2015-2016 烟台大学计算机与控制工程学院