Diqun Yan (严迪群)

Ph.D, Associate Professor
Department of Computer Science
Faculty of Electrical Engineering and Computer Science
Ningbo University, Jiangbei District, Ningbo, 315211 China.
Academic: yandiqun@nbu.edu.cn
Personal: yandiqun@gmail.com
ORCID ID：https://orcid.org/0000-0002-5241-7276
Find Me:

Short Bio.

Diqun Yan is currently an Associate Professor at the Faculty of Electrical Engineering and Computer Science in Ningbo University, Ningbo, Zhejiang, China. He is the head of Computer Science Department. He received the BS degree in Electrical Automation, the MS degree in Circuit and System, the PhD degrees in Communication and Information System from Ningbo University in 2002, 2008, 2012, respectively. He was a Visiting Scholar with New Jersey Institute of Technology, Newark, NJ, USA, from 2014 to 2015. His current research interests include speech processing and multimedia forensics.

Publications

Journal Papers

Kailai Shen, Diqun Yan, Jing Hu, Zhe Ye: Non-intrusive speech quality assessment: A survey. Neurocomputing, 127471 (2024)
Jiale Chen, Li Dong, Rangding Wang, Diqun Yan, Chengbin Peng: Mixed-Bit Sampling Graphic: When Watermarking Meets Copy Detection Pattern. IEEE Signal Processing Letters, 31: 286 - 290 (2023)
Peiwen Zhuo, Diqun Yan, Kaiyu Ying, Rangding Wang, Li Dong: Audio steganography cover enhancement via reinforcement learning. Signal, Image and Video Processing, (2023)
Kailai Shen, Diqun Yan, Li Dong: MSQAT: A multi-dimension non-intrusive speech quality assessment transformer utilizing self-supervised representations. Applied Acoustics, 212:109584 (2023)
Kailai Shen, Diqun Yan, Zhe Ye, Xianbo Xu, JinXing Gao, Li Dong, Chengbin Peng & Kun Yang: Non-intrusive speech quality assessment with attention-based ResNet-BiLSTM. Signal, Image and Video Processing, 17: 3377-3385 (2023)
Lang Chen, Rangding Wang, Li Dong, Diqun Yan: Imperceptible adversarial audio steganography based on psychoacoustic model. Multimedia Tools and Applications, 82:26451-26463 (2023)
Zhe Ye, Diqun Yan, Li Dong, Jiacheng Deng, Shui Yu: Stealthy Backdoor Attack Against Speaker Recognition Using Phase-Injection Hidden Trigger. IEEE Signal Processing Letters, 30:1057-1061 (2023)
Mingyu Dong, Diqun Yan, Yongkang Gong: Adversarial example devastation and detection on speech recognition system by adding random noise. Journal of the Audio Engineering Society, 71(1-2): 34-44 (2023)
Mingyu Dong, Diqun Yan, Rangding Wang: Adversarial examples protect your privacy on speech enhancement system. Computer Systems Science and Engineering, 46(1), 1-12 (2023)
Jinxing Gao, Diqun Yan, Mingyu Dong: Black-box adversarial attacks through speech distortion for speech emotion recognition. EURASIP J. Audio Speech Music. Process., 2022(1): 20 (2022)
Hui Xiao, Li Dong, Hao Xu, Shuibo Fu, Diqun Yan, Kangkang Song, Chengbin Peng: Semi-supervised semantic segmentation with cross teacher training. Neurocomputing, 508: 36-46 (2022)
Yi Xie, Xianliang Jiang, Guang Jin, Ziyi Jiang, Diqun Yan: NLPC: A nimble low-priority congestion control algorithm for high-speed and lossy networks. J. King Saud Univ. Comput. Inf. Sci., 34(Issue 10, Part B): 9052-9059 (2022)
Jiacheng Deng, Li Dong, Rangding Wang, Rui Yang, Diqun Yan: Decision-Based Attack to Speaker Recognition System via Local Low-Frequency Perturbation. IEEE Signal Process. Lett., 29: 1432-1436 (2022)
Tianyun Liu, Diqun Yan, Nan Yan, Gang Chen: Anti-forensics of fake stereo audio using generative adversarial network. Multim. Tools Appl., 81(12): 17155-17167 (2022)
Kaiyu Ying, Rangding Wang, Yuzhen Lin, Diqun Yan: Adaptive Audio Steganography Based on Improved Syndrome-Trellis Codes. IEEE Access, 9: 11705-11715 (2021)
Lang Chen, Rangding Wang, Diqun Yan, Jie Wang: Learning to Generate Steganographic Cover for Audio Steganography Using GAN. IEEE Access, 9: 88098-88107 (2021)
Donghua Wang, Li Dong, Rangding Wang, Diqun Yan: Fast speech adversarial example generation for keyword spotting system with conditional GAN. Comput. Commun., 179: 145-156 (2021)
Jie Wang, Rangding Wang, Li Dong, Diqun Yan, Xueyuan Zhang, Yuzhen Lin: Towards breaking DNN-based audio steganalysis with GAN. Int. J. Auton. Adapt. Commun. Syst., 14(4): 371-383 (2021)
Tianyun Liu, Diqun Yan, Rangding Wang, Nan Yan, Gang Chen: Identification of Fake Stereo Audio Using SVM and CNN. Inf., 12(7): 263 (2021)
Yuzhen Lin, Rangding Wang, Li Dong, Diqun Yan, Jie Wang: Tackling the Cover Source Mismatch Problem in Audio Steganalysis With Unsupervised Domain Adaptation. IEEE Signal Process. Lett., 28: 1475-1479 (2021)
Diqun Yan, Mingyu Dong, Jinxing Gao: Exposing Speech Transsplicing Forgery with Noise Level Inconsistency. Security and Communication Networks, 6659271: 1-6 (2021)
Diqun Yan, Yongkang Gong, Tianyun Liu: Antiforensics of Speech Resampling Using Dual-Path Strategy. Wireless Communications and Mobile Computing, 6649196: 1-8 (2021)
Diqun Yan, Xiaowen Li, Li Dong, Rangding Wang: An Antiforensic Method against AMR Compression Detection. Security and Communication Networks, 8849902: 1-8 (2020)
Donghua Wang, Li Dong, Rangding Wang, Diqun Yan, Jie Wang: Targeted Speech Adversarial Example Generation With Generative Adversarial Network. IEEE Access, 8: 124503-124513 (2020)
Xueyuan Zhang, Rangding Wang, Diqun Yan, Li Dong, Yuzhen Lin:Selecting Optimal Submatrix for Syndrome-Trellis Codes (STCs)-Based Steganography With Segmentation. IEEE Access, 8: 61754-61766 (2020)
Heng Yu, Rangding Wang, Li Dong, Diqun Yan, Yongkang Gong, Yuzhen Lin: A High-Capacity Reversible Data Hiding Scheme Using Dual-Channel Audio. IEEE Access, 8: 162271-162278 (2020)
Biaoli Tao, Rangding Wang, Diqun Yan, Chao Jin: Anti-Forensics of Double Compressed MP3 Audio. International Journal of Digital Crime and Forensics, 12(3): 45-57 (2020)
Dong Li, Jiantao Zhou, Diqun Yan, Rangding Wang: First Steps Toward Concealing the Traces Left by Reversible Image Data Hiding. IEEE Transactions on Circuits and Systems II: Express Briefs, DOI: 10.1109/TCSII.2020.2981550 (2020)
Yongchao Ye, Lingjie Lao, Diqun Yan*, Rangding Wang: Identification of Weakly Pitch-Shifted Voice Based on Convolutional Neural Network. International Journal of Digital Multimedia Broadcasting, 8927031: 1-10 (2020)
Xiaowen Li, Diqun Yan*, Li Dong, Rangding Wang: Anti-Forensics of Audio Source Identification Using Generative Adversarial Network. IEEE Access, 7(1): 184332-184339 (2019)
Diqun Yan*, Li Xiang, Zhifeng Wang, Rangding Wang: Detection of HMM Synthesized Speech by Wavelet Logarithmic Spectrum. Automatic Control and Computer Sciences, 53(1): 72-79 (2019)
Chao Jin, Rangding Wang, Diqun Yan: Source smartphone identification by exploiting encoding characteristics of recorded speech. Digital Investigation 29: 129-146 (2019)
Zhifeng Wang, Diqun Yan*, Rangding Wang, Li Xiang and Tingting Wu: Speech Resampling Detection Based on Inconsistency of Band Energy. CMC: Computers, Materials & Continua 56(2): 247-259 (2018)
Qijuan Huang, Rangding Wang, Diqun Yan, Jian Zhang: AAC Double Compression Audio Detection Algorithm Based on the Difference of Scale Factor. Information 9(7): 161 (2018)
Tianyun Qin, Rangding Wang, Diqun Yan, Lang Lin: Source Cell-Phone Identification in the Presence of Additive Noise from CQT Domain. Information 9(8): 205 (2018)
Diqun Yan*, Rangding Wang, Jinglei Zhou, Chao Jin, Zhifeng Wang: Compression history detection for MP3 audio. TIIS 12(2): 662-675 (2018)
Chao Jin, Rangding Wang, Diqun Yan: Steganalysis of MP3Stego with low embedding-rate using Markov feature. Multimedia Tools Appl. 76(5): 6143-6158 (2017)
Chao Jin, Rangding Wang, Diqun Yan, Pengfei Ma, Jinglei Zhou: An efficient algorithm for double compressed AAC audio detection. Multimedia Tools Appl. 75(8): 4815-4832 (2016)
Xianmin Yu, Rangding Wang, Diqun Yan, Pengfei Ma: Detecting Fake-Quality MP3 based on Huffman Table Index. JSW 9(4): 907-912 (2014)
Pengfei Ma, Rangding Wang, Diqun Yan, Chao Jin: Detecting double-compressed MP3 with the Same Bit-rate. JSW 9(10): 2522-2527 (2014)
Juan Li, Rangding Wang, Diqun Yan, Youming Li: A multipurpose audio aggregation watermarking based on multistage vector quantization. Multimedia Tools Appl. 68(3): 571-593 (2014)
Diqun Yan*, Rangding Wang: Detection of MP3Stego exploiting recompression calibration-based feature. Multimedia Tools Appl. 72(1): 865-878 (2014)
Diqun Yan*, Rangding Wang, Xianmin Yu, Jie Zhu: Steganalysis for MP3Stego using differential statistics of quantization step. Digital Signal Processing 23(4): 1181-1185 (2013)
Xianmin Yu, Rangding Wang, Diqun Yan: Detecting MP3Stego using calibrated side information features. JSW 8(10): 2628-2636 (2013)
Diqun Yan*, Rangding Wang, Xianmin Yu, Jie Zhu: Steganography for MP3 audio by exploiting the rule of window switching. Computers & Security 31(5): 704-716 (2012)
Diqun Yan*, Rangding Wang: Huffman table swapping-based steganograpy for MP3 audio. Multimedia Tools Appl. 52(2-3): 291-305 (2011)
Diqun Yan*, Rangding Wang, Liguang Zhang: Quantization Step Parity-based Steganography for MP3 Audio. Fundam. Inform. 97(1-2): 1-14 (2009)

Conference Papers

Kailai Shen, Diqun Yan, Li Dong, Ying Ren, Xiaoxun Wu, Jing Hu: SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction. IEEE ASRU, 2023: 1-6
Zhe Ye, Diqun Yan, Li Dong, Kailai Shen: Breaking Speaker Recognition with PaddingBack. ICASSP 2024 (Accepted)
JiaCheng Deng, Li Dong, Jiahao Chen, Diqun Yan, Rangding Wang, Dengpan Ye, Lingchen Zhao, Jinyu Tian: Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition. ACM MM 2023: 7559-7568
Huazheng Hao, Hui Xiao, Li Dong, Diqun Yan, Dongtai Liang, Jiayan Zhuang, Chengbin Peng: A Pseudo-Dual Self-Rectification Framework for Semantic Segmentation. ICME 2023: 408-413
Xianbo Xu, Diqun Yan, Li Dong: Adaptive-SpEx: Local and Global Perceptual Modeling with Speaker Adaptation for Target Speaker Extraction. SMC 2023: 342-347
Xiaojian Ji, Li Dong, Rangding Wang, Diqun Yan, Yang Yin, Jinyu Tian: Gradient Sign Inversion: Making an Adversarial Attack a Good Defense. IJCNN 2023: 1-6
Zhimin He, Jiangbo Qian, Diqun Yan, Chong Wang, Yu Xin: Animal Re-Identification Algorithm for Posture Diversity. ICASSP 2023: 1-5
Zhe Ye, Terui Mao, Li Dong, Diqun Yan: Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion. INTERSPEECH 2023: 4923-4927
Jiale Chen, Li Dong, Rangding Wang, Diqun Yan, Weiwei Sun & Hang-Yu Fan: Physical Anti-copying Semi-robust Random Watermarking for QR Code. IWDW 2022: 131-146
Jiacheng Deng, Terui Mao, Diqun Yan, Li Dong, Mingyu Dong: Detection of Synthetic Speech Based on Spectrum Defects. DDAM@MM 2022: 3-8
Ning Lu, Li Dong, Diqun Yan, Xianliang Jiang: On Attacking Deep Image Quality Evaluator Via Spatial Transform. SMC 2022: 2876-2881
Terui Mao, Diqun Yan, Yongkang Gong, Randing Wang: Identification of Synthetic Spoofed Speech with Deep Capsule Network. FCS 2021: 257-265
Kaiyu Ying, Rangding Wang, Diqun Yan: Iteratively Generated Adversarial Perturbation for Audio Stego Post-processing. WIFS 2021: 1-6
Donghua Wang, Rangding Wang, Li Dong, Diqun Yan, Yiming Ren: Efficient Generation of Speech Adversarial Examples with Generative Model. IWDW 2020: 251-264
Diqun Yan, Tingting Wu: Detection of Various Speech Forgery Operations Based on Recurrent Neural Network. SPDE 2020: 415-426
Jie Wang, Rangding Wang, Li Dong, Diqun Yan: Robust, Imperceptible and End-to-End Audio Steganography Based on CNN. SPDE 2020: 427-442
Donghua Wang, Rangding Wang, Li Dong, Diqun Yan, Xueyuan Zhang, Yongkang Gong: Adversarial Examples Attack and Countermeasure for Speech Recognition System: A Survey. SPDE2020: 443-468
Xueyuan Zhang, Rangding Wang, Li Dong, Diqun Yan, Yuzhen Lin, Jie Wang: Towards Designing an Effective Complexity Indicator for Audio Steganography. ICC 2020: 1-6
Xueyuan Zhang, Rangding Wang, Li Dong, Diqun Yan: Post-processing for Enhancing Audio Steganographic Undetectability. SPDE2020: 546-559
Tingting Wu, Diqun Yan*, Li Xiang, Rangding Wang: Detection of Operation Type and Order for Digital Speech. CSMT 2020: 25-37
Yuzhen Lin, Rangding Wang, Diqun Yan, Li Dong, Xueyuan Zhang: Audio Steganalysis with Improved Convolutional Neural Network. IH&MMSec 2019: 210-215
Yongchao Ye, Lingjie Lao, Diqun Yan*, Lang Lin: Detection of Replay Attack Based on Normalized Constant Q Cepstral Feature. ICCCBDA 2019: 407-411
Lang Lin, Rangding Wang, Diqun Yan, Can Li: A Replay Voice Detection Algorithm Based on Multi-feature Fusion. ICCCS 2018: 289-299
Qijuan Huang, Rangding Wang, Diqun Yan, Jian Zhang: AAC Audio Compression Detection Based on QMDCT Coefficient. ICCCS 2018: 347-359
Lang Lin, Rangding Wang, Diqun Yan: A Replay Speech Detection Algorithm Based on Sub-band Analysis. Intelligent Information Processing 2018: 337-345
Biaoli Tao, Rangding Wang, Diqun Yan, Chao Jin, Yanan Chen, Li Zhang: Audio Tampering Detection Based on Quantization Artifacts. ICCCS 2016: 430-439
Chao Jin, Rangding Wang, Diqun Yan, Biaoli Tao, Yanan Chen, Anshan Pei: Source Cell-Phone Identification Using Spectral Features of Device Self-noise. IWDW 2016: 29-45
Jinglei Zhou, Rangding Wang, Chao Jin, Diqun Yan: Multiple MP3 Compression Detection Based on the Statistical Properties of Scale Factors. IWDW 2015: 51-60
Chao Jin, Rangding Wang, Diqun Yan, Pengfei Ma, Kaiyun Yang: A novel detection scheme for MP3Stego with low payload. ChinaSIP 2014: 602-606
Jinglei Zhou, Rangding Wang, Chao Jin, Diqun Yan: Detecting Fake-Quality WAV Audio Based on Phase Differences. IWDW 2014: 525-534
Pengfei Ma, Rangding Wang, Diqun Yan, Chao Jin: A Huffman Table Index Based Approach to Detect Double MP3 Compression. IWDW 2013: 258-271
Diqun Yan, Rangding Wang: Reversible Data Hiding for Audio Based on Prediction Error Expansion. IIH-MSP 2008: 249-252

Rewards

"VoiceMOS Challenge: ASRU 2023. Ranked 1st (Team 03) in Singing Voice Conversion Track, and Ranked 2nd (Team 03) in French Speech Synthesis Track.

Fundings

"Cross-domain Steganography for MP3 Audio against Statistical Detection", Scholar Program of National Natural Science Foundation of China (NSFC) under Grant No. 61300055, 2014-2016. PI
"Identification of Digital Spoofing Speech based on Feature Self-learning", Science Foundation of Zhejiang Province under Grant No. LY17F020010, 2017-2019. PI
"Global Forgery Detection of Digital Speech based on Deep Learning", Natural Science Foundation under Grant No. 2017A610123, 2016-2018. PI
"Research on Security Strategy for Digital Multimedia in New Mobile Internet", Scientific and Technical Key Innovation Team of New Generation Mobile Internet Client Software under Grant No. 2012R10009-05, 2011-2013. PI

Professional Activities

Association: Committee Member of CCF Distributed Computing and Processing. Committee Member of CSIG Digital Media Forensics and Security
Reviewer: IEEE Transactions on Information Forensics and Security, IEEE Signal Processing Letters, Digital Signal Processing, Multimedia Tools and Applications, IWDW.

Students

Current

Sheng Ling (Master Student, 2023)
Yuheng Huang (Master Student, 2023) Thesis: Backdoor Attacking
Jiazheng Jia (Master Student, 2023) Thesis: Adversarial Example
Site Wu (Master Student, 2023) Thesis: Speech Forensics
Xiaoxun Wu (Master Student, 2023) Thesis: Non-intrusion Speech Quality Assessment
Ying Ren (Master Student, 2022) Thesis: Backdoor Attacking
Wenjie Zhang (Master Student, 2022) Thesis: Adversarial Example
Jiahong Ye (Master Student, 2022) Thesis: Speech Forensics
Kailai Shen (Master Student, 2021) Thesis: Non-intrusion Speech Quality Assessment
Xianbo Xu (Master Student, 2021) Thesis: Target Speaker Extraction
Zhe Ye (Master Student, 2021) Thesis: Backdoor Attacking for Speaker Recognition
Hanzi Zhang(Master Student, 2019, on-the-job)
Shiyi Xie(Master Student, 2017, on-the-job) Thesis: Identification of Speech Scene Forgery

Graduated

Mingyu Dong (Master Student, 2020, Hangzhou Dianzi University, Ph.D.) Thesis: Positive Research of Adversarial Examples in Speech Recognition
Jinxing Gao (Master Student, 2020) Thesis: Research on Privacy Protection Technology Based on Speech Feature Vector
Tianyun Liu (Master Student, 2019, Jiaxing Research Institute of Zhejiang University) Thesis: Identification of Fake Stereo Audio
Terui Mao (Master Student, 2019, Ningbo City College of Vocational Technology) Thesis: Speech Deepfake Detection
Yongkang Gong (Master Student, 2018, SoundAI) Thesis: Countermeasure for Adversarial Speech
Tingting Wu (Master Student, 2017, China Telecom) Thesis: Detection of Operation Type and Order for Digital Speech
Xiaowen Li (Master Student, 2017, The Affiliated Hospital of Medical School of Ningbo University) Thesis: Anti-Forensics of Audio Source Identification and Double Compression Detection
Yongchao Ye (Bachelor Student, 2020, Master Student in Southern Univeristy of Science and Technology)
Li Xiang (Master Student, 2016, Hunan Mobile Communication Co., Ltd.) Thesis: Forensics of Digital Speech Processing History
Zhifeng Wang (Master Student, 2016) Thesis: Anti-Forensics of Digital Audio Resampling and Recompression
Fan Yang (Master Student, 2015, Shanghai Shanda Network Development Co., Ltd.) Thesis: Detecting Speech Splicing based on Noise Level Inconsistency
Hongwei Xu (Master Student, 2015, Zhejiang Electric Power Corporation) Thesis: Identification of Electronic Disguised Voice
Li Zhang(Master Student, 2014, Shenzhen Xiaohua Technology) Thesis: Identification of Computer-generated Speech and Natural Speech

Teachings

Information Security (for Undergraduate Student): Fall Semester
Digital Speech Processing (for Undergraduate Student): Spring Semester
Computer Organization (for Undergraduate Student): Spring Semester
Advance Technologies in Information Security (for Graduate Student): Fall Semester
Speech Recognition (for Graduate Student): Spring Semester