Curriculum Vitae

  Education

• B.S. in Electronic Information Engineering, USTC, 2015.9 - 2019.7
• Ph.D student in Information and Communication Engineering, USTC, 2019.9 - 2024.7 (expected)

  Experience

• Jun. 2020 - Present: Microsoft Research Asia (MSRA)
  • Research Intern at Internet Media (IM) Group
  • Mentor: Chong Luo
  • Research Projects:
    • Text-based speech editing.
    • Unsupervised modal-agnostic content-style decomposition.
    • General-purposed speech representation learning.
    • ASR-friendly speech enhancement.
  • Engineering Project:
    • Real-time speaker number estimator for Microsoft PowerPoint.
• Aug. 2018 - Aug. 2019: Microsoft Research Asia (MSRA)
  • Research Intern at Internet Media (IM) Group
  • Mentor: Chong Luo
  • Research Projects:
    • Monaural speech enhancement.
    • Exploratory attempt on Dense Video Captioning.
  • Engineering projects:
    • Transfer the proposed speech enhancement method PHASEN into product.
    • Develop a mobile app that generates couplets from photos.

  Research Interest

Speech editing: Focusing on achieving free manipulation of speech signals in a computational approach.

  Research Topics

• Speech editing
• Speech enhancement
• Representation learning
• Content-style decomposition

  Publications

PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network.

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion

  Hobbies

• Bass, guitar, clarinet, music composing.
• Board game
• Jogging