李琳
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:
说话人识别,智能语音处理,机器学习等
主讲课程:
《电路分析》,省级精品在线开放课程/线上线下混合式一流课程,课程负责人
《电子线路I》
学术兼职:
国际IEEE学会会员
CCF语音对话与听觉专业委员会会员
全国人机语音通讯会议(NCMMSC)常设机构委员会委员
华东地区高校“电子线路”课程教学研究会副秘书长
成果奖励:
福建省科学技术进步奖二等奖(2020)
福建省教学成果奖二等奖(2020)
厦门市科学技术进步奖一等奖(2020)
第十届厦门大学青年教师技能大赛理工科组一等奖暨最佳课件奖(2015)
厦门大学首届“我最喜爱的十位教师”之一(2013)
课题项目:
小样本说话人识别的泛化建模与迁移方法研究,国家自然科学基金项目,2020.01-2023.12,主持
EDA创新技术研究,科技部国家重点研发计划项目,2020.01-2023.12,任务负责人
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,厦门大学新型冠状病毒防治应急科研攻关项目,2020.02-2020.09,主持
基于气动模型的肺部病理特征分析方法研究,福建省中青年教师教育科研项目,2018.06-2020.12,主持
代表作:
著作:
《语音识别:原理与应用》,洪青阳,李琳,电子工业出版社,2020年6月。
《电子线路实验》,刘舜奎,李琳,刘恺之,电子工业出版社,2022年6月。
论文:
[1] Lin Li*, Fuchuan Tong, and Qingyang Hong. When Speaker Recognition Meets Noisy Labels: Optimizations for Front-ends and Back-ends, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, 30:1586-1599.
[2] Fuchuan Tong#, Tao Li#, Dexing Liao, Shipeng Xia, Song Li, Qingyang Hong*, and Lin Li*, The XMUSPEECH System for Accented English Automatic Speech Recognition. Applied Sciences-Basel, 2022, 12, 1478(1-8).
[3] Fuchuan Tong, Lingling Liu, Xingjia Xie, Qingyang Hong, and Lin Li*. Respiratory Sound Classification: From Fluid-solid Coupling Analysis to Feature-band Attention, IEEE Access, 2022, 10: 22018-22031.
[4] Lin Li*, Zheng Li, Yan Liu, and Qingyang Hong, Deep Joint Learning for Language Recognition, Neural Networks, 2021,141:72-86.
[5] 胡文轩,王秋林,李松,洪青阳,李琳,基于端到端的多语种语音识别研究,信号处理,2021,37(10):1816-1824.
[6] Lin Li, Shaoyu Lin, Shuli Shen, Kongcheng Wu, Xiaochao Li *, and Yihui Chen, High-throughput and Area-efficient Fully-pipelined Hashing Cores Using BRAM in FPGA, Microprocessors and Microsystems, 2019, 67: 82-92.
[7] Qingyang Hong, Lin Li*, Jun Zhang, Lihong Wan, and Huiyang Guo, Transfer Learning for PLDA-based Speaker Verification, Speech Communication, 2017, 92: 90-99.
[8] 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.
[9] 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.
[10] Fuchuan Tong, Siqi Zheng, Haodong Zhou, Xingjia Xie, Qingyang Hong, and Lin Li*, Deep Representation Decomposition for Rate-invariant Speaker Verification, Odyssey 2022, June 28-July 01 2022, pp. 228-232.
[11] Fuchuan Tong, Siqi Zheng, Min Zhang, Yafeng Chen, Hongbin Suo, Qingyang Hong, and Lin Li*, Graph Convolutional Network based Semi-supervised Learning on Multi-speaker Meeting Data, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, May 2022, pp.6622-6626.
[12] Song Li, Beibei Ouyang, Dexin Liao, Shipeng Xia, Lin Li*, and Qingyang Hong, End-to-end Multi-accent Speech Recognition with Unsupervised Accent Modelling, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, June 2021, pp. 6418-6422.
[13] Song Li, Beibei Ouyang, Lin Li*, and Qingyang Hong, Light-TTS: Lightweight Multi-Speaker Multi-Lingual Text-To-Speech, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, June 2021, pp. 8383-8387.
[14] Fuchuan Tong, Miao Zhao, Jianfeng Zhou, Zheng Li, Lin Li *, and Qingyang Hong, ASV-subtools: Open Source Toolkit for Automatic Speaker Verification, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, June 2021, pp. 6184-6188.
[15] Hao Lu, Jianfeng Zhou, Miao Zhao, Wendian Lei, Qingyang Hong, and Lin Li*, XMU-TS Systems for NIST SRE19 CTS Challenge, IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 2020, pp.7569-7573.
[16] Rongjin Li, Miao Zhao, Zheng Li, Lin Li*, Qingyang Hong, Anti-Spoofing Speaker Verification System with Multi-Feature Integration and Multi-Task Learning, Interspeech, Graz, Austria, August 2019, pp.2883-2887.
[17] 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, Interspeech, Graz, Austria, August 2019, pp.2883-2887.
[18] Jianfeng Zhou, Tao Jiang, Lin Li*, Qingyang Hong, Zhe Wang, Bingyin Xia, Training Multi-Task Adversarial Network for Extracting Noise-Robust Speaker Embedding, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12-17 May 2019, pp. 6196-6200.
专利:
(1) Lin Li, Zheng Li, Qingyang Hong, Multi-type acoustic feature integration method and system based on deep neural networks, Date of Patent: Jan. 4, 2022, Paten No.: US 11,217,225 B2.
(2) 李琳, 李松, 洪青阳,轻量级多说话人语音合成系统及电子设备,申请日:2020/10/26,授权日:2022/7/8,专利号:ZL202011159299.7,授权公告号:CN 112133282B
(3) 李琳,刘浩杰,郭东辉,一种面向模拟集成电路的器件对称约束检测方法,申请日:2020/10/27,授权日:2022/5/20,专利号:ZL202011160909.5,授权公告号:CN112287633B
(4) 李琳,黎荣晋,洪青阳,一种基于深度神经网络的欺骗语音检测方法,申请日:2019年7月2日,授权日:2021年9月17日,专利号:ZL201910590712.6,授权公告号:CN 110491391B
(5) 李琳,柳玲玲,洪青阳,郭东辉,基于深度神经网络架构的肺音识别方法、装置和设备,申请日:2020年8月13日,授权日:2021年7月6日,专利号:ZL202010815366.X,授权公告号:CN111956259B
(6) 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
(7) 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