Yurii Halychanskyi

Portrait of Yurii Halychanskyi

Yurii Halychanskyi

About Me

I am a PhD student at the University of Illinois Urbana-Champaign (UIUC), co-advised by Volodymyr Kindratenko and Mark Hasegawa-Johnson. My research focuses on generative audio modeling for cross-domain conversion, including tasks such as timbre and accent transfer in low-resource or unsupervised settings.

Publications

Preprint

SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings

Priyam Mazumdar*, Yurii Halychanskyi*, Steven Guo, Mark Hasegawa-Johnson, Volodymyr Kindratenko.

* Equal contribution

[Paper]
Learning to Listen: ICML 2026 Workshop on ML for Audio Oral

Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson, Dilek Hakkani-Tür, Volodymyr Kindratenko.

[Paper] [Demo]
Preprint

Accent Conversion: A Problem-Driven Survey of Sociolinguistic and Technical Constraints

Yurii Halychanskyi, Jianfeng Steven Guo, Volodymyr Kindratenko.

[Paper]
ICASSP 2026 Poster

FAC-FACodec: Controllable Zero‑Shot Foreign Accent Conversion with Factorized Speech Codec

Yurii Halychanskyi, Cameron Churchwell, Yutong Wen, Volodymyr Kindratenko.

[Paper] [Demo]
ICASSP 2025 Poster

Latent diffusion bridges for unsupervised musical audio timbre transfer

Michele Mancusi*, Yurii Halychanskyi*, Kin Wai Cheuk, Eloi Moliner, Chieh-Hsin Lai, Stefan Uhlich, Junghyun Koo, Marco A Martínez-Ramírez, Wei-Hsiang Liao, Giorgio Fabbro, Yuki Mitsufuji.

* Equal contribution

[Paper] [Demo]

Research Experience

Meta

London, United Kingdom
Research Scientist Intern
Summer 2026

Sony AI

Tokyo, Japan
Research Scientist Intern
Summer 2024

Machine Learning for Science (ML4SCI)

Remote
Research Scientist Intern (Google Summer of Code)
Summer 2021, Summer 2022

Education

University of Illinois Urbana‑Champaign

Urbana, IL
PhD in Computer Science
Aug 2023 – May 2028 (Expected)

University of Washington

Seattle, WA
B.S. in Computer Science
2021 – 2023

Presentations

Will present Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When? at the Learning to Listen: ICML 2026 Workshop on Machine Learning for Audio in Seoul, Korea. Upcoming · July 10, 2026
Presented FAC-FACodec: Controllable Zero‑Shot Foreign Accent Conversion with Factorized Speech Codec at ICASSP 2026 — session SLP-P6: Neural Vocoders and Codecs. Tuesday, May 5, 2026 · 14:00–16:00
Presented FAC-FACodec: Controllable Zero‑Shot Foreign Accent Conversion with Factorized Speech Codec at the 4th Annual NCSA Student Research Conference. April 23, 2026
Presented FAC-FACodec: Controllable Zero‑Shot Foreign Accent Conversion with Factorized Speech Codec and Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When? at Midwest Speech and Language Days (MSLD) 2026. April 15, 2026