徐珑婷 副教授

发布者:信息科学与技术学院发布时间:2019-04-26浏览次数:8921




个人简介

女,1989年生,东华大学信息科学与技术学院副教授、硕导。20116月毕业于南京邮电大学通信工程专业,获工学学士学位。20174月毕业于南京邮电大学信息与通信工程专业,获工学博士学位;博士期间于20147月至20167月于新加坡科技局实习两年。20178月至20187月于新加坡国立大学参加博士后研究。曾参与过国家自然科学基金重点项目等多项科研课题的研究工作。


研究方向

人工智能中语音信号处理方向的研究,主要包括说话人识别、伪造语音检测、语音水印、语音信号特征提取等。


教育背景

2007.9–2011.6 南京邮电大学 通信与信息工程学院  学士(保研)

2011.9–2017.4 南京邮电大学 通信与信息工程学院 博士(硕博连读)

2014.7–2016.7, 新加坡科技研究局 信息通讯研究院 博士访学  


工作经历

2017.7–2018.7, 新加坡国立大学 电气工程和计算机系 博士后  

2018.10–至今 东华大学 信息科学与技术学院 讲师、副教授


近五年承担的科研项目‍‍

1.自适应电致变色器件基础研究(2022.1-2026.12),国家自然科学基金重点项目,参与;

2.录音回放攻击下说话人识别系统的模型研究(2021.1-2023.12),国家自然科学基金青年科学基金项目,主持;

3.移动边缘计算框架下软件定义车联网智能安全数据传输机制研究(2020.1-2023.12),国家自然科学基金面上基金项目,参与;

4.远场说话人识别系统的后端技术研究(2019.5-2022.4),上海市青年科技英才扬帆计划,主持;

5.短时语音下的说话人识别的关键技术研究(2019.3-2020.3),东华大学青年教师科研启动基金资助项目,主持;

6.短语音说话人识别中鲁棒模型的技术研究(2019.1-2021.12),东华大学中央高校基本科研业务费专项资金,自由探索项目,主持.


近五年代表性论文

[1] Xu, L., Yang, J., ,You, C., Qian, X., Huang, D.. Device Features Based on Linear Transformation With Parallel Training Data for Replay Speech Detection, 2023, IEEE/ACM Transactions on Audio Speech and Language Processing.

[2] Zhai, M., Chen, Y., Xu, L., Yin, W.. An End-to-End Neural Network for Complex Electromagnetic Simulations, 2023, IEEE Antennas and Wireless Propagation Letters.

[3] He, M., Ali, Z. S. F. , Tian, M., Shan, Z., Jiang, Z., & Xu, L.. Modified Cepstral Feature for Speech Anti-spoofing2023, Journal of Dong Hua University(English Edition).

[4] Han, S., Wang, C., & Xu, L.. A Decision Level Identity Fusion Based Prediction Model for Smooth Fluctuation Products, 2022, IEEE 5th International Conference on Electronic Information and Communication Technology.

[5]Guo, X., Huang, D., Xu, L.. A robust zero-watermarking scheme based on non-negative matrix factorization for audio protection, 2022, PLOS ONE.

[6] Ali, Z. S. F. & Xu, L.. Implementation of Multiple Feature Selection Algorithms for Speech Spoofing Detection, 2022, Journal of Physics: Conference Series.

[7] Zhao, P. , Tao, J. , Rauf, A. , Jia, F. , & Xu, L. . Load balancing for energy-harvesting mobile edge computing, 2021, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences.

[8] Lu, X., Zhang, J., Yang, D., Xu, L.. Cascaded Convolutional Neural Network-Based Hyperspectral Image Resolution Enhancement via an Auxiliary Panchromatic Image, 2021IEEE TRANSACTIONS ON IMAGE PROCESSING.

[9] Xu, L., Wei, Z., Zaidi, S. F. A., Ren, B., & Yang, J.. Speech enhancement based on nonnegative matrix factorization in constant-Q frequency domain, 2021, Applied Acoustics.

[10] Xu, L., Huang, D.,Zaidi, S. F. A., Rauf, A., Das, R. K.. Graph Fourier Transform Based Audio Zero-Watermarking, 2021, IEEE SIGNAL PROCESSING LETTERS.

[11] Xu, L., Huang, D., Guo, X., Rao, W., Ji, Y., & Li, R.. A Novel Robust Zero-Watermarking Algorithm for Audio Based on Sparse Representation, 2021, China Communications.

[12] Ji, Y., Xu, L., & Zhu, W.. Adversarial dictionary learning for monaural speech enhancement, 2020, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH.

[13] Yang, J., Xu, L., Ren, B., & Ji, Y.. Discriminative features based on modified log magnitude spectrum for playback speech detection, 2020, EURASIP Journal on Audio, Speech, and Music Processing.

[14] Xu, L., Ren, B., Zhang, G., & Yang, J.. Linear transformation on x-vector for text-independent speaker verification, 2019, IET Electronics Letters.

[15] Yang, J., Xu, L., & Ren, B. Constant-Q Deep Coefficients for Playback Attack Detection, 2019 IEICE Transactions on Information and Systems.

[16] Chen, H., Xu, L., & Yang, Z.. Multi-dimensional speaker information recognition with multi-task neural network, 2018, IEEE 4th International Conference on Computer and Communications.

[17] Lee, K. A., Hautamki, V., Kinnunen, T. H., Yamamoto, H., Todisco, M. Xu, L.. I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences, 2019, INTERSPEECH.

[18] Xu, L., Das, R., Yilmaz, E., Generative x-vectors for text-independent speaker verification, 2018, IEEE Spoken Language Technology Workshop (SLT).

[19] Xu, L., Lee, K. A., Li, H., & Yang, Z. Co-whitening of I-vectors for Short and Long Duration Speaker Verification, 2018, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH.

[20] Xu, L., Lee, K. A., Li, H., & Yang, Z.. Generalizing I-Vector Estimation for Rapid Speaker Recognition, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.


近五年代表性专利

1.徐珑婷; 张光林; 赵萍; 张磊; 季云云, 矢量x-vector线性变换下的说话人识别方法,授权公告日:2021.08.20.

2.赵萍;黄代玉;徐珑婷, 车联网中基于博弈的位置数据中毒攻击原型系统, 授权公告日:2021.05.11.

3. 徐珑婷; 魏郅林; 季云云; 张光林; 贾逢德, 一种基于恒定常数频域变换下的语音增强方法. 授权公告日: 2020.07.10.

4.张磊; 赵康宁; 倪琴; 徐珑婷; 张光林,复杂室内环境下一种基于改进粒子滤波的无线定位方法,申请公布日: 2019.10.15


主讲课程

模式识别、信息论、工程与社会、感测技术等


联系信息

电子邮箱:xlt@dhu.edu.cn