RESEARCH OUTPUT
Publications
Work on spatial audio, acoustic reconstruction, and audio generation.
Full citation records are available on Google Scholar ↗.
13 records · journal and conference papers, preprints, a meeting abstract, and a thesis
2026
Journal2026HRTF
Xingyu Chen, Hanwen Bi, Fei Ma, Sipei Zhao, Eva Cheng, Ian S. Burnett
The Journal of the Acoustical Society of America, 160(5), 3663–3674
Explicitly modeling dependencies across frequency improves HRTF reconstruction from sparse spatial measurements.
Preprint2026Audio generation
Xingyu Chen, Fei Ma, Sipei Zhao
arXiv:2609.27598
Distributional post-training improves pretrained text-to-audio generators while preserving one-step inference.
Preprint2026HRTF
Xingyu Chen, Hanwen Bi, Sipei Zhao, Fei Ma, Eva Cheng, Ian S. Burnett
arXiv:2609.25995
GeoAtt uses geometry-aware, query-conditioned aggregation to support varying measurement counts and layouts with a single model.
2025
Conference2025Sound field
Xingyu Chen, Sipei Zhao, Fei Ma, Eva Cheng, Ian S. Burnett
31st International Congress on Sound and Vibration (ICSV31), 1–8
A permutation-invariant model combines acoustic reciprocity and the Helmholtz equation for reconstruction across source and receiver regions.
Conference2025Sound field
Yile Angela Zhang, Wei-Ting Lai, Amy Bastine, Xingyu Chen, Lachlan I. Birnie, Thushara D. Abhayapala, Prasanga N. Samarasinghe
APSIPA Annual Summit and Conference (APSIPA ASC), 447–452
Acoustic responses identify devices sharing a room to help reduce cross-device feedback in teleconferencing.
Thesis2025Sound field
Xingyu Chen
MPhil thesis, Australian National University
Deep learning for sound field estimation, HRTF interpolation, and speech enhancement on drones.
2024
Conference2024Speech
Xingyu Chen, Hanwen Bi, Wei-Ting Lai, Fei Ma
18th International Workshop on Acoustic Signal Enhancement (IWAENC), 85–89
Adapter-based transfer learning adapts a pretrained speech enhancement model to drone noise.
Conference2024Sound field
Wei-Ting Lai, Lachlan Birnie, Xingyu Chen, Amy Bastine, Thushara D. Abhayapala, Prasanga N. Samarasinghe
18th International Workshop on Acoustic Signal Enhancement (IWAENC), 31–35
2023
Conference2023Sound field
Xingyu Chen, Fei Ma, Amy Bastine, Prasanga Samarasinghe, H. Sun
APSIPA Annual Summit and Conference (APSIPA ASC)
Physical constraints guide sound field estimation around a rigid sphere from limited spatial measurements.
Preprint2023HRTF
Xingyu Chen, Fei Ma, Yile Zhang, Amy Bastine, Prasanga N. Samarasinghe
arXiv:2309.08290
Spherical convolution captures the spatial structure of HRTFs through spherical harmonic representations.
Preprint2023HRTF
Fei Ma, Thushara D. Abhayapala, Prasanga N. Samarasinghe, Xingyu Chen
arXiv:2307.14650
The Helmholtz equation provides a physical constraint for reconstructing HRTFs at unmeasured directions.
Meeting abstract2023HRTF
Xingyu Chen, Fei Ma, Prasanga N. Samarasinghe
The Journal of the Acoustical Society of America, 154(4_supplement), A183
2022
Journal2022Other
X. Li, H. Jiang, Xingyu Chen, H. Kong, J. Wu
IEEE Robotics and Automation Letters, 7(4), 10705–10712
No matching publications. Try another topic or search term.
Publication records checked against Google Scholar in November 2026. Preprints, meeting abstracts, and the thesis are labeled separately.