基本信息

 

 

 

丁宁,博士,二级教授。

国家级高层次人才

研究领域

大模型的算法和应用

人机交互

自然语言处理

语音处理

 

联系方式

人工智能学院

人工智能与机器人研究所

 

地址:西安市碑林区咸宁西路28逸夫科学馆

邮编:710049

Email:ding.ning[at]xjtu.edu.cn

(为了避免垃圾邮件,请手动将[at]改为@)

我的新闻

站点计数器

公告

欢迎对本研究方向感兴趣的硕士、博士、博士后加入,有意者请附上个人简历和成绩单,Email联系。

 

本课题组可以为您提供:

  1. 最前沿的技术
  2. 科研和实际应用的双重能力(双重洗礼)
  3. 阿里,字节跳动等国内一线大厂的实习机会
  4. 美国,日本,新加坡,欧洲等海外名校的交流机会

 

对候选人的期望为(按照优先顺序):

  1. 态度好:对科研的热情,努力,执着,自驱
  2. 数学好:对人工智能相关理论的学习,理解,创新
  3. 编程好:至少熟悉一门编程语言,种类不限,动手能力强
  4. 英语好:阅读和撰写英文文献,与国际同行交流(PK)
  5. 身体好:work hard, play hard

教育经历

20019-20057    ,获学士学位

20059-20087    ,获硕士学位

20089-20123    庆应大学(日本),获博士学位

工作经历

20124月–20209     东芝株式会社(日本),Research Scientist

20209月–20236     阿里巴巴,算法总监

20238月–至今           ,教授

专著

  1. N. Hamada, and N. Ding, “Source Separation and DOA Estimation for Underdetermined Auditory Scene” in Soundscape Semiotics - Localisation and Categorisation, H. Glotin, Eds, Publisher: InTech, 2014.

期刊论文

  1. Jianlong Wu, Wei Sun, Tian Gan, Ning Ding, Feijun Jiang, Jialie Shen and Liqiang Nie “Neighbor-Guided Consistent and Contrastive Learning for Semi-Supervised Action Recognition”, IEEE Trans. on Image Processing, Vol. 32, pp 2215 – 2227, 2023.

  2. N. Ding and N. Hamada, “DOA estimation of multiple speech sources from a stereophonic mixture in underdetermined case”, IEICE Trans. on Fundamental, Vol.E95-A No.4, pp735-744, 2012.

  3. N. Ding, M. Yoshida, J. Ono, and N. Hamada, “Blind source separation using sequential phase difference versus frequency distribution”, Journal of Signal Processing, vol. 15, No. 5, pp. 375-385, 2011.

  4. W. Kasprzak, N. Ding, and N. Hamada, “Speaker localization and speech separation in two echoic mixtures”, Science-Future of Lithuania, vol. 3, No.1, pp. 43-49, 2011,

  5. W. Kasprzak, N. Ding, and N. Hamada, “Relaxing the WDO assumption in blind extraction of speakers from speech mixtures”, Journal of Telecommunications and Information Technology, vol. 4, pp. 50-58, 2010.

  6. N. Ding, Y.F. Fan, and G. Niu, “A summary of Surface-conduction Electron-emitter Display”, Vacuum Electronics, vol.2, pp. 15-18, 2007.

国际会议

  1. Jianlong Wu, Haozhe Yang, Tian Gan, Ning Ding, Feijun Jiang, Liqiang Nie, CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning.  CVPR 2023.

  2. Haozhe Yang, Xianqiang Gao, Jianlong Wu, Tian Gan, Ning Ding, Feijun Jiang and Liqiang Nie, Self-adaptive Context and Modal-interaction Modeling For Multi-modal Emotion Recognition. ACL 2023

  3. Zorilă, C., Li, M., Hayakawa, D., Liu, M., Ding, N., Doddipatla, R. (2020) Toshiba’s Speech Recognition System for the CHiME 2020 Challenge, ICASSP 2020, pp.62-66, May. 2020

  4. H. Fujimura, N. Ding, D. Hayakawa, and T. Kagoshima, “Simultaneous Flexible Keyword Detection and Text-dependent Speaker Recognition for Low-resource Devices”, ICPRAM 2020, pp.297-307, Valletta, Malta, Feb. 2020.

  5. K. Fujimoto, N. Ding, and N. Hamada, “Multiple Sources' Direction Finding by using Reliable Component on Phase Difference Manifold and Kernel Density Estimator”, ICASSP 2012, pp.2601-2604, Kyoto, Japan, Mar. 2012.

  6. N. Ding and N. Hamada, “DOA estimation in underdetermined stereophonic mixture by kernel density estimator,” ISPACS 2011, pp.1-5, Chiangmai, Thailand, Dec. 2011.

  7. N. Ding and N. Hamada, “Speaker localization and speech separation using phase difference versus frequency distribution,” EUSIPCO 2011, pp.250-253, Barcelona, Spain, Aug. 2011.

  8. M. Sekigawa, M. Yoshida, N. Ding, and N. Hamada, “Speech separation and localization by exploiting constraints on delay-time vector introduced by array configuration”, NCSP’11, pp.239-242, Tianjin, China, Mar. 2011.

  9. N. Ding and N. Hamada, “DOA estimation by Hough transform in phase difference distribution versus frequency,” ISPACS 2010, pp. 277-280, Chengdu, China, Dec. 2010.

  10. M. Yoshida, N. Ding, and N. Hamada, “Blind speech separation by integrating three pairs of phase differences of equilateral triangular microphone array,” ISPACS 2010, pp. 201-204, Chengdu, China, Dec. 2010.

  11. J. Ono, N. Ding, and N. Hamada, “Sound Source Localization using Phase-Dierence vs Frequency Plots,” APSIPA  ASC 2010, pp.46, Biopolis, Singapore, Dec. 2010.

  12. N. Ding, M. Yoshida, J. Ono, and N. Hamada, “Speech mixture separation and DOA estimation utilizing sequence of phase difference distribution”, NCSP’10, pp.341-344, Honolulu, Hawaii, U.S.A., Mar. 2010.

  13. W. Kasprzak, N. Ding, and N. Hamada, “Blind localization and separation of two speakers based on two mixtures”, Proceedings of 2nd IEEE Workshop on Bio-Inspired Signal and Image Processing (BISIP), On CD-ROM, Vilnius, Lithuania, Mar. 2010

  14. M. Kitagaki, C.L. Wang, N. Ding, X.Y. Zhang, G. Uchida, S.L. Wu, T. Shinoda, and H. Kajiyama, “Cathode Luminescence Study of MgO”. IDW’08, pp.1999-2000, Niigata, Japan, Dec. 2008.

国内会议

  1. 丁寧,籠嶋岳彦,藤村浩司,田中大貴,早川大智,“少量キーワード発話データによるキーワード検出適応手法”.信学技報, vol. 119, no. 398, SP2019-48, pp. 25-29, 20201.

  2. 丁寧,籠嶋岳彦,“多人数音声認識向け回り込み音声の抑圧方法”.日本音響学会2017年秋季研究発表会,松山,2017年9月.

  3. 丁寧,木田祐介,広畑誠,“音韻情報と方向情報を用いた発話間距離による話者クラスタリング”.日本音響学会2014年秋季研究発表会,札幌,2014年9月.

  4. N. Ding, 藤本健, 浜田望, “Kernel density estimator approach for solving underdetermined source localization problem from arbitrary microphone configuration”, 26 信号処理シンポジウム, pp.422-427, 札幌, 201111.

  5. N. Ding, T. Shimada, M. Yoshida, J. Ono, W. Kasprzak and N. Hamada, “A consideration on time-frequency masking methods for speech separation”, 24 信号処理シンポジウム, pp.209-214, 鹿児島, 200911.

授权专利

  1. 丁宁,藤村浩司,信息处理装置及信息处理方法CN112420020B,2024.5.3

  2. 吴建龙,杨浩哲,高先强,聂礼强,甘甜,丁宁,姜飞俊,基于动态上下文表示和模态融合的多模态分类方法及系统CN116089906B,2023.6.16

  3. 吴建龙,丁沐河,聂礼强,董雪,甘甜,丁宁,姜飞俊,基于预习机制知的模型压缩方法及系统,CN115294407B,2023.1.3

  4. 建龙,孙玮,聂礼强,甘甜,李潇婕,丁宁,姜飞俊,基于近邻一致性和对比学习的半监督视频分类方法及系统,CN115311605B,2023.1.3

  5. Ning Ding, Hiroshi Fujimura, Information processing apparatus, keyword detecting apparatus, and information processing method, United States 11961510, April 16, 2024

  6. Ning Ding, Hiroshi Fujimura, Information processing apparatus and information processing method, United States 11823669, November 21, 2023

  7. Ning Ding, Makoto Hirohata, Speech processing device, speech processing method, and computer program productUnited States 10832685, November 10, 2020

  8. Ning Ding, Takehiko Kagoshima, Voice processing device, voice processing method, and computer program product, United States 10504523, December 10, 2019

  9. Ning Ding, Yusuke, Kida, Sound source direction estimation apparatus, sound source direction estimation method and computer program product, United States 9473849, October 18, 2016

  10. Ning Ding, Yusuke, Kida, Makoto Hirohata, Speech processing apparatus and method, United States 9460714, October 4, 2016

  11. 丁寧藤村浩司、情報処理装置、情報処理方法およびプログラム,日本特許第7191792号,2022.12.9

  12. 丁寧藤村浩司、情報処理装置、キーワード検出装置、情報処理方法およびプログラム,日本特許第7098587号,2022.07.1

  13. 丁寧音声認識装置、音声認識方法及びプログラム,日本特許第6903613号,2021.06.25

  14. 丁寧、籠嶋岳彦、音声処理装置、音声処理方法およびプログラム,日本特許第6800809号,2020.11.27

  15. 丁寧、広畑誠、音声処理装置、音声処理方法及び音声処理プログラム,日本特許第6556575号,2019.07.19

  16. 丁寧、木田祐介、音源方向推定装置、音源方向推定方法およびプログラム,日本特許第6289936号,2018.02.16

  17. 丁寧、木田祐介、広畑誠、音声処理装置、方法、及びプログラム,日本特許第6158006号,2017.06.16

科研项目

没有找到条目。
项目编号 项目名称 项目来源 起讫时间 承担角色 项目类别
2023ZD0121300 大模型系统能力涌现机理与激发机制研究 科技创新2030-“新一代人工智能”重大项目 2024-01~2026-12 负责人 纵向项目