Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.13834 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912931321479168 |
|---|---|
| author | Lu, Minhui Reiss, Joshua D. |
| author_facet | Lu, Minhui Reiss, Joshua D. |
| contents | We present a physics-informed voiced backend renderer for singing-voice synthesis. Given synthetic single-channel audio and a fund-amental--frequency trajectory, we train a time-domain Webster model as a physics-informed neural network to estimate an interpretable vocal-tract area function and an open-end radiation coefficient. Training enforces partial differential equation and boundary consistency; a lightweight DDSP path is used only to stabilize learning, while inference is purely physics-based. On sustained vowels (/a/, /i/, /u/), parameters rendered by an independent finite-difference time-domain Webster solver reproduce spectral envelopes competitively with a compact DDSP baseline and remain stable under changes in discretization, moderate source variations, and about ten percent pitch shifts. The in-graph waveform remains breathier than the reference, motivating periodicity-aware objectives and explicit glottal priors in future work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13834 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Vocal-Tract Area and Radiation with a Physics-Informed Webster Model Lu, Minhui Reiss, Joshua D. Sound Audio and Speech Processing We present a physics-informed voiced backend renderer for singing-voice synthesis. Given synthetic single-channel audio and a fund-amental--frequency trajectory, we train a time-domain Webster model as a physics-informed neural network to estimate an interpretable vocal-tract area function and an open-end radiation coefficient. Training enforces partial differential equation and boundary consistency; a lightweight DDSP path is used only to stabilize learning, while inference is purely physics-based. On sustained vowels (/a/, /i/, /u/), parameters rendered by an independent finite-difference time-domain Webster solver reproduce spectral envelopes competitively with a compact DDSP baseline and remain stable under changes in discretization, moderate source variations, and about ten percent pitch shifts. The in-graph waveform remains breathier than the reference, motivating periodicity-aware objectives and explicit glottal priors in future work. |
| title | Learning Vocal-Tract Area and Radiation with a Physics-Informed Webster Model |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.13834 |