About me

This is Pengjie Shen’s homepage. I am a Ph.D. student in Computer Science and Technology at Inner Mongolia University, focusing on speech signal processing. My research spans several closely related areas:

  • Speech Separation – designing algorithms that disentangle overlapping speakers in noisy or reverberant environments
  • Speech Enhancement – improving intelligibility and perceptual quality for both human listeners and downstream ASR systems
  • Target Speaker Extraction – isolating a desired voice from multi‑speaker mixtures using limited enrollment data
  • Multi‑Channel Microphone Array Processing – leveraging spatial cues and beamforming strategies to boost robustness under real‑world acoustic conditions

Publications

  • Jiahui Pan, Pengjie Shen, Hui Zhang, Xueliang Zhang. Efficient multi-channel speech enhancement with spherical harmonics injection for directional encoding. In Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2024) DOI ·

  • Jiahui Pan, Pengjie Shen, Hui Zhang, Xueliang Zhang. Innovative directional encoding in speech processing: leveraging spherical harmonics injection for multi-channel speech enhancement. In Proceedings of the Thirty‑Third International Joint Conference on Artificial Intelligence (IJCAI 2024) DOI ·

  • Pengjie Shen, Xueliang Zhang, Zhong-Qiu Wang. ARiSE: Auto-Regressive Multi-Channel Speech Enhancement. In Proc. INTERSPEECH 2025 (to appear, accepted) DOI ·

Under Review

  • Pengjie Shen, Kangrui Chen, Shulin He, Pengru Chen, Shuqi Yuan, He Kong, Xueliang Zhang, Zhong-Qiu Wang Listen to Extract: Onset-Prompted Target Speaker Extraction. Submitted to IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), under review Preprint ·