CV

Education

• Ph.D in Electronic Engineering and Computer Science, Queen Mary University of London, UK, 2022 ~ 2027 (expected)
• B.S. in Computer Science, National Chiao Tung University, Taiwan, 2014 ~ 2018

Work experience

• Summer 2024 - Winter 2024: Research Intern
  • Sony AI, Sony, Tokyo, Japan
  • Duties include: differentiable audio processing and audio mixing
  • Supervisor: Manager Wei-Hsiang Liao
• Winter 2020 - Summer 2022: Backend Engineer
  • Backend R&D, Rayark Inc., Taipei, Taiwan
  • Duties include: Design and implement mobile game servers
  • Supervisor: CTO Alvin
• Summer 2019 - Winter 2020: Engineer
  • Vive R&D, HTC, New Taipei City, Taiwan
  • Duties include: Applying Deep Learning Techniques on HRTF applications
  • Supervisor: VP Vasco Choi
• 2018: Research Assistant
  • Institute of Information Science, Academia Sinica, Taipei, Taiwan
  • Duties include: Doing Research on NN-based Vocoder Model/Developing End-to-End Music Transcription Model
  • Supervisor: Professor Li Su
• Summer 2017: Intern
  • Institute of Information Science, Academia Sinica, Taipei, Taiwan
  • Duties include: Developing Cepstrum-Based Music Transcription System
  • Supervisor: Professor Li Su

Skills

• Programming Language
  • C/C++
  • Python
  • Golang
  • Haskell
• Music Information Retrieval
  • Multi-Pitch Estimation
  • Source Separation
  • Voice Generation/Synthesis
• Machine Learning
• Deep Learning
• DSP
• Spatial Audio
  • Head Related Transfer Functions
• Qiskit (Quantum Programming)
• Music Production
  • Song Writing
  • Drums Editing
  • Mixing
• Musical Instruments
  • Piano
  • Violin
  • Electric Guitar

Demonstration

• 2025 Semester B, ECS515U - Signals and Systems Theory
  • Queen Mary University of London, UK
  • Module Organiser: Dr. Maged Elkashlan
• 2024 Semester B, ECS7006P - Music Informatics
  • Queen Mary University of London, UK
  • Module Organiser: Prof. Simon Dixon
• 2023 Semester A, ECS602U/ECS707P - Digital Signal Processing
  • Queen Mary University of London, UK
  • Module Organiser: Dr. Luk Arnaut

Reviewed

• 2026
  • ICASSP
• 2025
  • DMRN+20 Workshop
  • AI for Music Workshop @NeurIPS
  • DiffSys Workshop @EurIPS
  • ICASSP
  • ISMIR
  • AES AIMLA
• 2024
  • ICASSP
  • AAAI
  • IEEE TASLP x1
  • IEEE SPL x1
• 2023
  • DMRN+18 Workshop
  • AAAI

Publications

Accelerating Automatic Differentiation of Direct Form Digital Filters

Chin-Yun Yu and György Fazekas, "Accelerating Automatic Differentiation of Direct Form Digital Filters", 1st Workshop on Differentiable Systems and Scientific Machine Learning @ EurIPS 2025, December 2025.

Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior

Chin-Yun Yu, Marco A. Martínez-Ramírez, Junghyun Koo, Wei-Hsiang Liao, Yuki Mitsufuji and György Fazekas, "Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2025.

DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions

Chin-Yun Yu, Marco A. Martínez-Ramírez, Junghyun Koo, Ben Hayes, Wei-Hsiang Liao, György Fazekas and Yuki Mitsufuji, "DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions", International Conference on Digital Audio Effects (DAFx), September 2025.

Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method

Chin-Yun Yu and György Fazekas, "Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method", AES International Conference on Artificial Intelligence and Machine Learning for Audio, September 2025.

GOLF: A Singing Voice Synthesiser with Glottal Flow Wavetables and LPC Filters

Chin-Yun Yu and György Fazekas, "GOLF: A Singing Voice Synthesiser with Glottal Flow Wavetables and LPC Filters", Transactions of the International Society for Music Information Retrieval, December 2024.

Differentiable All-pole Filters for Time-varying Audio Systems

Chin-Yun Yu, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao, Joshua Reiss and György Fazekas, "Differentiable All-pole Filters for Time-varying Audio Systems", International Conference on Digital Audio Effects, September 2024.

Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis

Chin-Yun Yu and György Fazekas, "Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis", Proc. Interspeech, September 2024.

Time-of-arrival estimation and phase unwrapping of head-related transfer functions with integer linear programming

Chin-Yun Yu, Johan Pauwels, and György Fazekas, "Time-of-arrival estimation and phase unwrapping of head-related transfer functions with integer linear programming", Audio Engineering Society Convention 156, June 2024.

Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables

Chin-Yun Yu and György Fazekas, "Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables", International Society for Music Information Retrieval Conference, November 2023.

Zero-Shot Duet Singing Voices Separation with Diffusion Models

Chin-Yun Yu, Emilian Postolache, Emanuele Rodolà, and György Fazekas, "Zero-Shot Duet Singing Voices Separation with Diffusion Models", The ISMIR Sound Demixing Workshop, November 2023.

Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution

Chin-Yun Yu, Sung-Lin Yeh, György Fazekas, and Hao Tang, "Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution", IEEE International Conference on Acoustics, Speech and Signal Processing, June 2023.

Music Demixing Challenge 2021

Y Mitsuji, G Fabbro, S Uhlich, F-R Stöter, A Défossez, M Kim, W Choi, C-Y Yu, K-W Cheuk, "Music Demixing Challenge 2021", Front. Sig. Proc. 1:808395, January 2022.

Danna-Sep: Unite to separate them all

Chin-Yun Yu and Kin-Wai Cheuk, "Danna-Sep: Unite to separate them all", The ISMIR Workshop on Music Source Separation, November 2021.

Harmonic Preserving Neural Networks for Efficient and Robust Multipitch Estimation

Chin-Yun Yu, Jing-Hua Lin, and Li Su, "Harmonic Preserving Neural Networks for Efficient and Robust Multipitch Estimation", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, December 2020.

Multi-layered Cepstrum for Instantaneous Frequency Estimation

Chin-Yun Yu and Li Su, "Multi-layered Cepstrum for Instantaneous Frequency Estimation", IEEE Global Conference on Signal and Information Processing, Novermber 2018.

Talks

Introducing the 4A-2A plugin at DMRN+19

December 17, 2024

Talk at Queen Mary University of London, Mile End Campus, London, UK

Oral presentation of GOLF vocoder at ISMIR 2023

November 08, 2023

Talk at Politecnico di Milano, Leonardo Campus, Milan, Italy

NMF in PyTorch

September 19, 2020

Talk at Marine Ecoacoustics and Informatics Lab, Biodiversity Research Center, Academia Sinica, Nangang, Taipei