Yicheng Gu (she / her)

Bachelor Student,
School of Data Science
The Chinese University of Hong Kong, Shenzhen

Email: yichenggu@link.cuhk.edu.cn

Curriculum Vitae    /    Google Scholar    /    GitHub

About me

I'm a second-year Bachelor student at the Chinese University of Hong Kong, Shenzhen, supervised by Professor Zhizheng Wu and working closely with Xueyao Zhang. My ongoing works focus on Neural Vocoder and Differentiable Digital Signal Processing (DDSP). Recently, I'm participating in the development of the prototype of the open-source Amphion toolkit as one of the core numbers.

My research interests include:

  • Neural Vocoder
  • Differentiable Digital Signal Processing
  • Music Data Scaling Up
  • Audio-Visual Generation

Milestones
2023/12 My first paper about neural vocoder got accepted by ICASSP 2024.
2023/11 My first attempt at being a core member in the development of a large-scale open-source project.
2023/10 My first paper about singing voice processing got accepted by ML4Audio @ NeurIPS 2023.
2022/10 I entered Professor Zhizheng Wu's lab after I was admitted by The Chinese University of Hong Kong, Shenzhen as a Bachelor student.
Publications
ICASSP 2024   Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder
Yicheng Gu, Xueyao Zhang, Liumeng Xue, Zhizheng Wu
International Conference on Acoustics, Speech, and Signal Processing 2024
Paper / Code / Demo / Pretrained Model
TL;DR: We propose a Constant-Q Transform-based Discriminator for GAN-based neural vocoders.
   Amphion: An Open-Source Audio, Music and Speech Generation Toolkit
Xueyao Zhang*, Liumeng Xue*, Yicheng Gu*, Yuancheng Wang*, Haorui He, Chaoren Wang, Xi Chen, Zihao Fang, Haopeng Chen, Junan Zhang, Tze Ying Tang, Lexiao Zou, Mingxuan Wang, Jun Han, Kai Chen, Haizhou Li, Zhizheng Wu (*: Equal Contribution)
Technical Report / GitHub / HuggingFace / OpenXLab
TL;DR: We develop a unified audio generation open-source toolkit.
ML4Audio @ NeurIPS 2023   Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion
Xueyao Zhang, Yicheng Gu, Haopeng Chen, Zihao Fang, Lexiao Zou, Liumeng Xue, Zhizheng Wu
Machine Learning for Audio Workshop (ML4Audio) at NeurIPS 2023
Preprint / Code / Demo / Pretrained Model / HuggingFace Space / OpenXLab App
TL;DR: We propose to utilize multiple content features for singing voice conversion.
submitted   An Investigation of Time-Frequency Representation Discriminators for High-Fidelity Vocoder
Yicheng Gu, Xueyao Zhang, Liumeng Xue, Haizhou Li, Zhizheng Wu
Paper / Code / Demo
TL;DR: We propose a Continuous Wavelet Transform-based Discriminator for GAN-based neural Vocoders.
submitted   FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
Yiming Zhang, Yicheng Gu, Yanhong Zeng, Zhening Xing, Zhizheng Wu, Kai Chen
TL;DR: We propose a Video-to-Audio generation pipeline with Audio-Visual Synchronization and Text-Editability.
Education
2022- Bachelor student in Computer Science, supervised by Professor Zhizheng Wu
School of Data Science (SDS), The Chinese University of Hong Kong, Shenzhen
Honors and Awards
2023 The Academic Performance Scholarship, Class B (Top 3%, 2023)
2022 "LanHuaYing" Scholarship (Top 10 admitted students in Zhejiang Province, 2022)