Education

• B.S. in Physics, Nanjing University, 2015
• M.S. in Acoustics, Nanjing University, 2018
• Ph.D in Electrcial Engineering, University of Rochester, 2024 (expected)

Work experience

• Summer 2023: Research intern
  • Adobe Research
  • Supervisor: Nick Bryan and Juan-Pablo Caceres
• Spring 2023: Part-time research intern
  • Ubisoft
  • Research Topic: Controllable high-quality sound effects generation
  • Supervisor: Marc-André Carbonneau
• Fall 2021~Fall 2022: Part-time research engineer
  • Adobe Research
  • Research Topic: Deployment of robust voice activity detection and filler word detection
  • Supervisor: Juan-Pablo Caceres and Justin Salamon
• Summer 2021: Research intern
  • Adobe Research
  • Research Topic: Robust voice activity detection and filler word detection
  • Supervisor: Justin Salamon and Juan-Pablo Caceres
• Fall 2020: Research intern
  • Kuaishou Technology
  • Research Topic: Lyrics onset detection and singing voice conversion
  • Supervisor: Baigong Zheng and Zhiyao Duan

Publications

Y-Vector: Multiscale Waveform Encoder for Speaker Embedding

A Study of the Robustness of Raw Waveform Based Speaker Embeddings Under Mismatched Conditions

Filler Word Detection and Classification: A Dataset and Benchmark

Music Source Separation with Generative Flow

Transcription Free Filler Word Detection with Neural semi-CRFs

EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis

MusicHiFi: Fast High-Fidelity Stereo Vocoding

Cacophony: An Improved Contrastive Audio-Text Model

Presto! Distilling Steps and Layers for Accelerating Music Generation