I am an assistant professor at Duke KunShan University. Prior to that, I was an assistant professor at Singapore Institute of Technology from October 2023 to July 2025 and a postdoctoral researcher at the National Institute of Informatics (NII), Japan, from 2021 to 2023, supervised by Prof Junichi Yamagishi. I received my Ph.D. degree from the Institute of Acoustics, Chinese Academy of Sciences/University of Chinese Academy of Sciences, in 2021, supervised by Prof Pengyuan Zhang. During 2018 and 2019, I was at the University of Kent, UK, as a Visiting Student, supervised by Prof Ian McLoughlin.

My research interest includes speech security, speaker and language recognition, and machine learning. I am a co-organizer of the VoicePrivacy challenge 2022, 2024, 2026 and Attacker Challenge at ICASSP 2025. My work has been published at the top international AI conferences and journals such as IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), IEEE Transactions on Information Forensics and Security (TIFS), Neural Networks, Computer Speech and Language (CSL), ICASSP, INTERSPEECH.

Teaching

• COMSCI311, Computer Networks, DKU undergraduate course
• COMSCI101, Introduction to Computer Science, DKU undergraduate course
• COMSCI302, Computer Vison, DKU undergraduate course
• ECE590K, Programing and Data Structures for Machine Learning, Duke master course
• AAI3001, Deep Learning and Computer Vision, SIT undergraduate course
• INF2008, Machine Learning, SIT undergraduate course

Projects as PI

• 2022-2023 JSPS KAKENHI Grant-in-Aid for Research Start-up (22K21319): Language-independent speaker anonymization with multiple privacy-related attributes, Budget: 2.2M JPY.
• 2024-2025 MOE Ignition Grant (R-IE3-A405-0005): Generative AI Aided Safety Investigation System, Budget: 180K SGD (Including 30K cash contribution from Singapore SMRT).
• 2024-2026 MOE AcRF Tier 1 (R-R13-A405-0005): User-centric Personalized Voice Protection, Budget: 150K SGD.
• 2025-2026 Division of Natural and Applied Sciences (DNAS) Interdisciplinary Seed Grants: A User-Centered study of Privacy Perceptions and mitigation in Multimodal Large Language Model Interactions.

Patent and License as the First Author

• Japanese patent: Deep-learning based speaker anonymization method.
• Japanese program commercial license granted by Japan Broadcasting Corporation (NHK): VocalGuard, a speaker anonymization program.

Academic Activities

• Organizer: Attacker Challenge at ICASSP 2025, VoicePrivacy Challenge 2024 and 2022.
• Session chair: ICASSP 2024, INTERSPEECH 2023, ISCSLP 2022.
• Reviewer: IEEE TASLP, IEEE TPAMI, IEEE SPL, CSL, ICASSP, INTERSPEECH, etc.

Publication

2026

• DAST: A Dual-Stream Voice Anonymization Attacker with Staged Training, Ridwan Arefeen, Xiaoxiao Miao, Tong Rong, Aik Beng Ng, Simon See, Timothy Liu, under review
• Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge, Ze Li, Xiaoxiao Miao, Juan Liu, Ming Li, under review
• Privacy Attacks on Voice Anonymization Systems: Overview and Key Findings from the First VoicePrivacy Attacker Challenge, Natalia Tomashenko, Xiaoxiao Miao, Emmanuel Vincent, Junichi Yamagishi, under review
• Toward Multimodal Industrial Fault Analysis: A Single-Speed Chain Conveyor Dataset with Audio and Vibration Signals, Zhang Chen, Yucong Zhang, Xiaoxiao Miao, Ming Li, under review
• Training Dynamics-Aware Multi-Factor Curriculum Learning for Target Speaker Extraction,Yun Liu, Xuechen Liu, Xiaoxiao Miao, Junichi Yamagishi, ICASSP, 2026
• ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks, Gabriel Lee Jun Rong, Christos Korgialas, Dion Jia Xu Ho, Pai Chet Ng, Xiaoxiao Miao, Konstantinos N Plataniotis, ICASSP Satellite Workshop, 2026
• The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymization, Natalia Tomashenko, Xiaoxiao Miao, Pierre Champion, Sarina Meyer, Michele Panariello, Xin Wang, Nicholas Evans, Emmanuel Vincent, Junichi Yamagishi, Massimiliano Todisco, submitted to CSL, 2026.

2025

• CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation, Crystal Min Hui Poon*, Pai Chet Ng*, Xiaoxiao Miao*, Immanuel Jun Kai Loh*, Bowen Zhang, Haoyu Song, Ian Mcloughlin, under review.
• Perturbation Self-Supervised Representations for Cross-Lingual Emotion TTS: Stage-Wise Modeling of Emotion and Speaker, Cheng Gong, Chunyu Qiang, Tianrui Wang, Yu Jiang, Yuheng Lu, Ruihao Jing, Xiaoxiao Miao, Xiaolei Zhang, Longbiao Wang, Jianwu Dang, submitted to Expert Systems With Applications.
• Target Speaker Extractor Training with Diverse Speaker Conditions and Synthetic Data, Yun Liu, Xuechen Liu, Xiaoxiao Miao, Junichi Yamagishi, APSIPA Transactions on Signal and Information Processing, 2025.
• MS-GAGA: Metric-Selective Guided Adversarial Generation Attack, Dion JX Ho, Gabriel Lee Jun Rong, Niharika Shrivastava, Harshavardhan Abichandani, Pai Chet Ng, Xiaoxiao Miao, PFATCV@BMVC25, 2025.
• SegReConcat: A Data Augmentation Method for Voice Anonymization Attack, Ridwan Arefeen, Xiaoxiao Miao, Tong Rong, Aik Beng Ng, Simon See, APCIPA ASC, 2025.
• Exploring Machine Learning and Language Models for Multimodal Depression Detection, Javier Si Zhao Hong, Timothy Zoe Delaya, Sherwyn Chan Yin Kit, Pai Chet Ng, Xiaoxiao Miao, APCIPA ASC, 2025.
• Speech Emotion Recognition via Entropy-Aware Score Selection, ChenYi Chua, JunKai Wong, Chengxin Chen, Xiaoxiao Miao, APCIPA ASC, 2025.
• SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization, Beilong Tang, Xiaoxiao Miao, Xin Wang, Ming Li, IEEE ASRU, 2025.
• The Risks and Detection of Overestimated Privacy Protection in Voice Anonymisation, Michele Panariello, Sarina Meyer, Pierre Champion, Xiaoxiao Miao, Massimiliano Todisco, Ngoc Thang Vu, Nicholas Evans, 5th Symposium on Security and Privacy in Speech Communication, 2025.
• Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling, Xuanjun Chen, Shih-Peng Cheng, Jiawei Du, Lin Zhang, Xiaoxiao Miao, Chung-Che Wang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang, under review, 2025.
• SecureSpeech: Prompt-based Speaker and Content Protection, Belinda Soh Hui Hui, Xiaoxiao Miao, Xin Wang, IEEE IJCB, 2025.
• Mitigating Language Mismatch in SSL-Based Speaker Anonymization, Zhe Zhang, Wen-Chin Huang, Xin Wang, Xiaoxiao Miao, Junichi Yamagishi, INTERSPEECH, 2025.
• Automated evaluation of children’s speech fluency for low-resource languages, Bowen Zhang, Nur Afiqah Abdul Latiff, Justin Kan, Rong Tong, Donny Soh, Xiaoxiao Miao, Ian McLoughlin, INTERSPEECH, 2025
• LSPnet: an ultra-low bitrate hybrid neural codec, Bowen Zhang, Ian McLoughlin, Xiaoxiao Miao, AS Madhukumar, INTERSPEECH, 2025
• The First VoicePrivacy Attacker Challenge, Natalia Tomashenko, Xiaoxiao Miao, Emmanuel Vincent, and Junichi Yamagishi, ICASSP, 2025.
• A benchmark for multi-speaker anonymization, Xiaoxiao Miao, Ruijie Tao, Chang Zeng, Xin Wang, IEEE TIFS, 2025.
• Adapting General Disentanglement-Based Speaker Anonymization for Enhanced Emotion Preservation, Xiaoxiao Miao*, Yuxiang Zhang*, Xin Wang, Natalia Tomashenko, Donny Cheng Lock Soh, Ian Mcloughlin, CSL, 2025.

2024

• Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches, Chang Zeng, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, SLT, 2024.
• Instructsing: High-Fidelity Singing Voice Generation Via Instructing Yourself, Chang Zeng, Chunhui Wang, Xiaoxiao Miao, Jian Zhao, Zhonglin Jiang, Yong Chen, SLT, 2024.
• The First VoicePrivacy Attacker Challenge Evaluation Plan, Natalia Tomashenko, Xiaoxiao Miao, Emmanuel Vincent, Junichi Yamagishi, arXiv, 2024.
• The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation, Michele Panariello, Natalia Tomashenko, Xin Wang, Xiaoxiao Miao, Pierre Champion, Hubert Nourtel, Massimiliano Todisco, Nicholas Evans, Emmanuel Vincent, Junichi Yamagishi, TASLP, 2024.
• The VoicePrivacy 2024 Challenge Evaluation Plan, Natalia Tomashenko, Xiaoxiao Miao, Pierre Champion, Sarina Meyer, Xin Wang, Emmanuel Vincent, Michele Panariello, Nicholas Evans, Junichi Yamagishi, Massimiliano Todisco, arXiv preprint, 2024.
• Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances, Chang Zeng, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, CSL, 2024.
• SynVox2: Towards a privacy-friendly VoxCeleb2 dataset, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, ICASSP, 2024.

2023

• VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research, Sarina Meyer*, Xiaoxiao Miao*, Ngoc Thang Vu, IEEE Open Journal of Signal Processing, 2023.
• Speaker Anonymization using Orthogonal Householder Neural Network, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko, TASLP, 2023.
• Speaker-Text Retrieval via Contrastive Learning, Xuechen Liu, Xin Wang, Erica Cooper, Xiaoxiao Miao, Junichi Yamagishi, arXiv preprint, 2023.
• Hiding speaker’s sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline, Paul-Gauthier Noé, Xiaoxiao Miao, Xin Wang, Junichi Yamagishi, Jean-François Bonastre, Driss Matrouf, ICASSP, 2023.

2022

• Attention back-end for automatic speaker verification with multiple enrollment utterances, Chang Zeng, Xin Wang, Erica Cooper, Xiaoxiao Miao, Junichi Yamagishi, ICASSP, 2022.
• Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, INTERSPEECH, 2022.
• Language-independent speaker anonymization approach using self-supervised pre-trained models, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko, Odyssey, 2022.
• GuidedMix: An on‐the‐fly data augmentation approach for robust speaker recognition system, Runqiu Xiao, Zhuo Li, Xiaoxiao Miao, Wenchao Wang, Pengyuan Zhang, Electronics Letters, 2022.

2021

• D-MONA: A dilated mixed-order non-local attention network for speaker and language recognition, Xiaoxiao Miao, Ian McLoughlin, Wenchao Wang, Pengyuan Zhang, Neural Networks, 2021.
• Variance Normalised Features for Language and Dialect Discrimination, Xiaoxiao Miao, Ian McLoughlin, Yan Song, Circuits, Systems, and Signal Processing, 2021.
• Adaptive Margin Circle Loss for Speaker Verification, Runqiu Xiao, Xiaoxiao Miao, Wenchao Wang, Pengyuan Zhang, Bin Cai, Liuping Luo, INTERSPEECH, 2021.

2020-2018

• A New Time–Frequency Attention Tensor Network for Language Identification, Xiaoxiao Miao, Ian McLoughlin, Yanyong Hong, Circuits, Systems, and Signal Processing, 2020.
• Lstm-tdnn with convolutional front-end for dialect identification in the 2019 multi-genre broadcast challenge, Xiaoxiao Miao, Ian McLoughlin, arXiv, 2019.
• A New Time-Frequency Attention Mechanism for TDNN and CNN-LSTM-TDNN, with Application to Language Identification, Xiaoxiao Miao, Ian McLoughlin, Yonghong Yan, INTERSPEECH, 2019.
• Improved conditional generative adversarial net classification for spoken language recognition, Xiaoxiao Miao, Ian McLoughlin, Shengyu Yao, Yonghong Yan, SLT, 2018.

Code

• Language-Independent Speaker Anonymization
• Multi-Speaker Anonymization
• Voice Anonymization Toolkit
• VoicePrivacy Challenge 2024
• VoicePrivacy Challenge 2026

  Award

• Outstanding reviewer award in INTERSPEECH, 2023
• Best paper nomination award in Odyssey, 2022
• The 2th place in MGB-5 challenge - Fine-grained Arabic Dialect Identification, ASRU, 2019
• Merit Student of University Chinese Academy of Science, 2018
• Best paper nomination award in NCMMSC, 2017