您所在的位置：首页  研究团队  导师  李琳教授
Prof. Lin Li
发布时间：2015-12-04　浏览次数：1685

李琳 博士


厦门大学电子工程系 教授、博士生导师

Email: Lilin@xmu.edu.cn

TEL:0592-2580135



学历

中国科学技术大学理学学士，电子信息科学与技术专业；

中国科学技术大学工学博士，电路与系统专业。


研究方向

  • 智能语音处理

  • EDA算法


主讲课程

  • 电路分析

  • 电子线路 I



学术兼职

  • 国际IEEE学会会员

  • NCMMSC常设机构委员会委员

  • CCF语音对话与听觉专业组委员

  • 华东地区高校“电子线路”课程教学研究会副秘书长


纵向项目

  • 国家自然科学基金，62001405，《小样本说话人识别的泛化建模与迁移方法研究》，2020-01至2023-12，在研，项目负责人。

  • 科技部国家重点研发计划项目，2019YFB2205000，《EDA创新技术研究》，2020-01至2023-12，在研，任务负责人。 

  • 厦门大学新型冠状病毒防治应急科研攻关项目，20720190143，《具有体温自动检测功能的医用防护服及无线监控设备开发》，2020-02至2020-09，已结题，主持。 

  • 福建省中青年教师教育科研项目，JT180010，《基于气动模型的肺部病理特征分析方法研究》，2018-06至2020-12，已结题，主持。


授权专利

(1)李琳，李铮，洪青阳，一种基于深度神经网络的多类声学特征整合方法和系统，申请日：2020年1月22日，授权日：2021年1月12日，专利号：ZL 202010073244.8，授权公告号：CN 111276131B

(2) 李琳，童峰，洪青阳，吴谨准，徐文皓，具有主动降噪和辅助诊断功能的电子听诊器，申请日：2016年1月15日, 授权日：2019年2月5日， 中国, 专利号：ZL201610027461.7，授权公告号：CN 105496447B



代表性论文

[1]Li Lin*; Li Zheng; Liu Yan; Hong Qingyang; Deep joint learning for language recognition, Neural Network, 2021, https://doi.org/10.1016/j.neunet.2021.03.026.

[2]Li Lin*; Lin Shaoyu; Shen Shuli; Wu Kongcheng; Li Xiaochao*; Chen Yihui; High-throughput and area-efficient fully-pipelined hashing cores using BRAM in FPGA, Microprocessors and Microsystems, 2019, 67: 82-92.  

[3]Hong Qingyang; Li Lin*; Zhang Jun; Wan Lihong; Guo Huiyang; Transfer learning for PLDA-based speaker verification, Speech Communication, 2017, 92: 90-99.    

[4]李琳; 万丽虹; 洪青阳*; 张君; 李明; 基于概率修正PLDA的说话人识别系统, 天津大学学报(自然科学与工程技术版), 2015, 48(08): 692-696.

[5]Yan Liu, Zheng Li, Lin Li* and Qingyang Hong. Phoneme-aware and Channel-wise Attentive Learning for Text Dependent Speaker Verification. Interspeech 2021.

[6]Fuchuan Tong, Yan Liu, Song Li, Jie Wang, Lin Li* and Qingyang Hong. Automatic Error Correction for Speaker Embedding Learning with Noisy Labels. INTERSPEECH 2021.

[7]Zheng Li, Yan Liu, Lin Li* and Qingyang Hong. Additive Phoneme-aware Margin Softmax Loss for Language Recognition. INTERSPEECH 2021.

[8]Song Li, Beibei Ouyang, Fuchuang Tong, Dexin Liao, Lin Li* and Qingyang Hong. Real-time End-to-End Monaural Multi-speaker Speech Recognition. INTERSPEECH 2021.

[9]Dexin Liao, Jing Li, Yiming Zhi, Song Li, Qingyang Hong, and Lin Li*. An Integrated Framework for Two-pass Personalized Voice Trigger. INTERSPEECH 2021.

[10]Jing Li, Binling Wang, Yiming Zhi, Zheng Li, Lin Li*, Qingyang Hong, and Dong Wang. Oriental Language Recognition (OLR) 2020: Summary and Analysis. INTERSPEECH 2021.

[11]Song Li, Beibei Ouyang, Dexin Liao, Shipeng Xia, Lin Li*, Qingyang Hong, End-to-end multi-accent speech recognition with unsupervised accent modelling, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

[12]Song Li, Beibei Ouyang, Lin Li*, Qingyang HongSong Li, Beibei Ouyang, Lin Li, Qingyang Hong, Light-TTS: Lightweight Multi-Speaker Multi-Lingual Text-To-Speech, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

[13]Tong Fuchuan, Zhao Miao, Zhou Jianfeng, Li Zheng, Li Lin*, Hong Qingyang, ASV-subtools: open source toolkit for automatic speaker verification, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

[14]Zheng Li, Miao Zhao, Lin Li*, Qingyang Hong, Multi-feature Learning with Canonical Correlation Analysis Constraint for Text-independent Speaker Verification, SLT2021.

[15]Song Li, Beibei Ouyang, Lin Li*, Qingyang Hong, Lightspeech: Lightweight Non-Autoregressive Multi-speaker Text-to-Speech, SLT2021.

[16]Zheng Li, Miao Zhao, Qingyang Hong, Lin Li*, Zhiyuan Tang, Dong Wang, Liming Song, Cheng Yang, AP20-OLR Challenge Three Tasks and Their Baselines, APSIPA2020.

[17]Song Li, Lin Li*, Qingyang Hong , Lingling Liu, Improving Transformer-based Speech Recognition with Unsupervised Pre-training and Multi-task Semantic Knowledge Learning, INTERSPEECH2020.

[18]Tao Jiang , Miao Zhao , Lin Li*, Qingyang Hong, The XMUSPEECH System for Short-Duration Speaker Verifification Challenge 2020, INTERSPEECH2020.

[19]Zheng Li, Miao Zhao, Jing Li, Lin Li*, Qingyang Hong, On the Usage of Multi-feature Integration for Speaker Verification and Language Identification, INTERSPEECH2020.

[20]Zheng Li, Miao Zhao, Jing Li, Yiming Zhi, Lin Li*, Qingyang Hong, The XMUSPEECH System for the AP19-OLR Challenge，INTERSPEECH2020.

[21]Hao Lu, Jianfeng Zhou, Miao Zhao, Wendian Lei, Qingyang Hong, Lin Li*, XMU-TS SYSTEMS FOR NIST SRE19 CTS CHALLENGE, ICASSP2020.

[22]Miao Zhao, Rongjin Li, Shijiang Yan, Zheng Li, Hao Lu, Shipeng Xia, Qingyang Hong and Lin Li*. Phone-aware Multi-task Learning and Length Expanding for Short-Duration Language Recognition, Asia-Pacific Signal and Information Processing Association (APSIPA), Lanzhou, China, November 18-21, 2019, EI

[23]Zheng Li, Hao Lu, Jianfeng Zhou, Lin Li* and Qingyang Hong. Speaker Embedding Extraction with Multi-feature Integration Structure, Asia-Pacific Signal and Information Processing Association (APSIPA), Lanzhou, China, November 18-21, 2019, EI

[24]Jianfeng Zhou, Tao Jiang, Qingyang Hong and Lin Li*. Extraction of Noise-Robust Speaker Embedding Based on Generative Adversarial Networks, Asia-Pacific Signal and Information Processing Association (APSIPA), Lanzhou, China, November 18-21, 2019, EI

[25]Rongjin Li, Miao Zhao, Zheng Li, Lin Li*, Qingyang Hong, Anti-Spoofing Speaker Verification System with Multi-Feature Integration and Multi-Task Learning, INTERSPEECH2019.

[26]Jianfeng Zhou, Tao Jiang, Zheng Li, Lin Li*, Qingyang Hong, Deep Speaker Embedding Extraction with Channel-Wise Feature Responses and Additive Supervision Softmax Loss Function, INTERSPEECH2019.

[27]Jianfeng Zhou, Tao Jiang, Lin Li*, Qingyang Hong, Zhe Wang, Bingyin Xia, Training Multi-Task Adversarial Network for Extracting Noise-Robust Speaker Embedding, ICASSP 2019.

[28]吴佳雯，刘沁婷，曾德炉，丁兴号，李琳，一种基于非参数贝叶斯理论的语音增强算法，厦门大学学报（自然科学版）, 2017,56(3):423-428. DOI:10.6043/j.issn. 0438-0479. 201702026.

[29]Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng*, Speech Enhancement Based on Nonparametric Factor Analysis, the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016), Tianjin, China, Oct. 17-20, 2016. EI: 20172303743540. 

[30]Lin Li, Wenhao Xu, Qingyang Hong, Feng Tong, Jinzhun Wu, Classification between normal and adventitious lung sounds using deep neutral network, the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016), Tianjin, China, Oct. 17-20, 2016. EI: 20172303743620. 

[31]李琳，徐文皓，洪青阳，童峰，吴谨准，颜卫源，基于最小分类误差准则的呼吸音分类技术，厦门大学学报（自然科学版），2016,55(06):901-905. DOI:10.6043/j. issn.0438-0479.201602021.

[32]Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, Delu Zeng, Saliency detection with spaces of background-based distribution, IEEE Signal Processing Letters, 2016, 23(5): 683-687. SCI. WOS:000375149800005.

[33]Qingyang Hong, Jun Zhang, Lin Li*, Lihong Wan, Feng Tong. A Transfer Learning Method for PLDA-based Speaker Verification, 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2016), Shanghai, 2016.3.20-2016.3.25.

[34]QiangYangHong, Lin Li*, Ming Li, Ling Huang, Lihong Wan, and Jun Zhang. Modified-prior PLDA and Score Calibration for Duration Mismatch Compensation in Speaker Recognition System. Pro Inter-speech, Dresden,German,pp: 1037-1041,Sep.6-10,2015.EI:20160902029411.

[35]Weicheng Cai, Ming Li,Lin Li, Qingyang Hong.Duration Dependent Convariance Regularization in PLDA  Modeling for Speaker Verification.Pro Inter-speech, Dresden,German,pp: 1027-1031, Sep.6-10, 2015. 

[36]黄玲，李琳*，王薇，易才钦，郭东辉.基于Sparse K-SVD学习字典的语音增强方法.厦门大学学报，第53卷第1期，页码: 36 - 40, 2014年1月.