Get in Touch

With Xiaoxiao Miao

Name and email
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Assistant Professor

Xiaoxiao Miao

Assistant Professor
PHD, Institute of Acoustics, Chinese Academy of Sciences/University Chinese Academy of Sciences, China
Cluster:
Infocomm Technology
Email
Google Scholar

Biography

Xiaoxiao Miao is an assistant professor at the Singapore Institute of Technology (SIT) since November 2023. She was a postdoctoral researcher at the National Institute of Informatics (NII), Japan from September 2021 to October 2023. She received the Ph.D. degree from the Institute of Acoustics, Chinese Academy of Sciences/University Chinese Academy of Sciences, in 2021. Her research interests include speech security, speaker and language recognition, and machine learning. She is a co-organizer of the VoicePrivacy challenge 2022 and 2024.

SIT Appointments

  • Assistant Professor
    – Present

Education

  • PHD
    Institute of Acoustics, Chinese Academy of Sciences/University Chinese Academy of Sciences , China
  • Bachelor
    North China Electric Power University (Beijing) , China

Achievements

  • 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
  • Merit Student of University Chinese Academy of Science
  • Best paper nomination award in NCMMSC2017

Professional Memberships

  • Member, Institute of Electrical and Electronics Engineers (IEEE)
  • Member, International Speech Communication Association(ISCA)

Corporate Experience

  • Reviewer for Computer Speech and Language, IEEE TPAMI, ICASSP, INTERSPEECH

Research Interests

  • Speech privacy, Speaker/language recognition, Machine learning

Past Projects

  • Language-independent speaker anonymization with multiple privacy-related attributes
    –

    JSPS KAKENHI Grant-in-Aid for Research Start-up (22K21319).  PI: Xiaoxiao Miao. Budget: 2.2 million Yen

     

  • VoicePersonae: Speaker identity cloning and protection
    –

    JST-ANR CREST Project (JPMJCR18A6) PI: Prof. Junichi Yamagishi

     

     

Journal Papers

  • Chang Zeng, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi. Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances. Computer Speech and Language. 86 (2024): 101619. doi: 10.1016/j.csl.2024.101619.

  • Sarina Meyer*, Xiaoxiao Miao*, Ngoc Thang Vu. VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research. IEEE Open Journal of Signal Processing. (2023): 1-10. doi: 10.1109/OJSP.2023.3344375.

  • Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko. Speaker Anonymization using Orthogonal Householder Neural Network. IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023): 3681-3695. doi: 10.1109/TASLP.2023.3313429.

  • Runqiu Xiao, Zhuo Li, Xiaoxiao Miao, Wenchao Wang, Pengyuan Zhang. GuidedMix: An onthefly data augmentation approach for robust speaker recognition system. Electronics Letters 58.5 (2022): 82-85. doi:https://doi.org/10.1049/ell2.12354.

  • Zhigao Chen, Xiaoxiao Miao, Runqiu Xiao, Wenchao Wang. Cross-domain speaker recognition using domain adversarial siamese network with a domain discriminator. Electronics Letters 56.14 (2021): 737-739. doi:https://doi.org/10.1049/el.2020.0673.

  • Xiaoxiao Miao, Jian Zhang, Hongbin Suo, Ruohua Zhou, Yanyong Hong. Expanding the length of short utterances for short-duration language recognition. Journal of Tsinghua University (Science and Technology) 58.3 (2018): 254-259. doi:10.16511/j.cnki.qhdxxb.2018.25.015.

  • Xiaoxiao Miao, Ian McLoughlin, Yan Song. Variance Normalised Features for Language and Dialect Discrimination. Circuits, Systems, and Signal Processing 40 (2021): 3621–3638. doi:https://doi.org/10.1007/s00034-020-01641-1.

  • Xiaoxiao Miao, Ian McLoughlin, Wenchao Wang, Pengyuan Zhang. D-MONA: A dilated mixed-order nonlocal attention network for speaker and language recognition. Neural Networks 139 (2021): 201-211. doi:https://doi.org/10.1016/j.neunet.2021.03.014

  • Xiaoxiao Miao, Ian McLoughlin, Yanyong Hong. A New Time–Frequency Attention Tensor Network for Language Identification. Circuits, Systems, and Signal Processing 39 (2020): 2744–2758. doi:https://doi.org/10.1007/s00034-019-01286-9.

  • Xiaoxiao Miao, Ji Xu, Jian Wang. Denoising Autoencoder-Based Language Feature Compensation. Journal of Computer Research and Development, 56.5 (2019): 1082-1091. doi:10.7544/issn1000-1239.2019.20180471.

Conferences

  • Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi. SynVox2: Towards a privacy-friendly VoxCeleb2 dataset. ICASSP 2024.

  • Chang Zeng, Xin Wang, Xiaoxiao Miao, Erica Cooper, Junichi Yamagishi. Improving generalization ability of countermeasures for new mismatch scenario by combining multiple advanced regularization terms. Interspeech 2023, 1998-2002

  • Paul-Gauthier Noé, Xiaoxiao Miao, Xin Wang, Junichi Yamagishi, Jean-François Bonastre, Driss Matrouf. Hiding speaker’s sex in speech using zero-evidence speaker representation in an analisis/synthesis pipeline. ICASSP 2023, 1-5.

  • Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko. Analyzing Language- Independent Speaker Anonymization Framework under Unseen Conditions. Proc. Interspeech 2022, 4426- 4430.

  • Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko. Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models. Proc. The Speaker and Language Recognition Workshop (Odyssey 2022), 279-286.

  • Chang Zeng, Xin Wang, Erica Cooper, Xiaoxiao Miao, Junichi Yamagishi. Attention back-end for automatic speaker verification with multiple enrollment utterances. ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6717-6721.

  • Runqiu Xiao, Xiaoxiao Miao, Wenchao Wang, Pengyuan Zhang, Bin Cai, Liuping Luo. Adaptive Margin Circle Loss for Speaker Verification. Proc. Interspeech 2021, 4618-4622.

  • Xiaoxiao Miao, Ian McLoughlin, Yanyong Hong. A New Time-Frequency Attention Mechanism for TDNN and CNN-LSTM-TDNN, with Application to Language Identification. Proc. Interspeech 2019, 4080-4084.

  • Xiaoxiao Miao, Ian McLoughlin, Yanyong Hong. Improved conditional generative adversarial net classification for spoken language recognition. 2018 IEEE Spoken Language Technology Workshop (SLT), 98-104.