ISIPLab

AHU. Hefei, Anhui, CHINA.

This is Intelligent Signal and Image Processing Lab at the Computer Science and Technogy Institute of Anhui University. Our research focuses on providing the state of the art technologies and exploring theories for modern signal and image processing. Specifically, we have proposed a series of fast real-value discrete Gabor transform theories and/or algorithms to efficiently perform signal transformation, the aim of which is to obtain a high resolution spectrum simultaneously in time and frequency domain. These technologies have been widely used in speech processing, time-frequency signal analysis, and image compression, et al.

In addition, we are interested in speech and image processing for the next generation of human-computer interface as well as for improving human health via intelligent signal processing methodology. For example, we have proposed efficient technologies for improving the communication quality of patients of laryngocarcinoma via transforming the whisper-like speech to the normal one. For improving the communication in very noisy environment, we provide the receiver a normal voiced speech which is obtained from the bone-conducted microphone, which can be widely used in noisy factory and military scenes. We also pay much attention to vein and palmprint recognition technology which has been successfully used in industry areas.

Currently, we also deliver part of our attention to physiological signal processing such as EEG for emotional conversion or recognition and brain PET signal for Alzheimer’s disease prediction.

news

Jan 21, 2023 Our Paper “A Novel Attention-Guided Generative Adversarial Network for Whisper-to-Normal Speech Conversion” was accepted by Cognitive Computation.

latest posts

May 20, 2025 Demo page for "CETTS"
May 8, 2025 Demo page for "MEDAF"

selected publications

  1. wave-mechanics.gif
    Multi-scale 3D-CRU for EEG emotion recognition
    Hao Dong, Jian Zhou, Cunhang Fan, and 3 more authors
    Biomedical Physics & Engineering Express, 2024
  2. wave-mechanics.gif
    Dynamic Ensemble Teacher-Student Distillation Framework for Light-weight Fake Audio Detection
    Jun Xue, Cunhang Fan, Jiangyan Yi, and 2 more authors
    IEEE Signal Processing Letters, 2024
  3. test img.png
    Multi-Level Information Aggregation Based Graph Attention Networks Towards Fake Speech Detection
    Jian Zhou, Yong Li, Cunhang Fan, and 2 more authors
    IEEE Signal Processing Letters, 2024
  4. wave-mechanics.gif
    A Novel Attention-Guided Generative Adversarial Network for Whisper-to-Normal Speech Conversion
    Teng Gao, Qing Pan, Jian Zhou, and 3 more authors
    Cognitive Computation, Jan 2023
  5. wave-mechanics.gif
    SETransformer: Speech Enhancement Transformer
    Weiwei Yu, Jian Zhou, HuaBin Wang, and 1 more author
    Cognitive Computation, May 2022
  6. brownian-motion.gif
    Multistage Model for Robust Face Alignment Using Deep Neural Networks
    Huabin Wang, Rui Cheng, Jian Zhou, and 2 more authors
    Cognitive Computation, May 2022