Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching

You Y, Qian Y, Qu T, Wang B, Lv X. Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching. In: Convention Paper. Audio Engineering Society; 2026.pp. 10293:1-. Available from: https://aes.org/publications/elibrary-page/?id=23190

@inproceedings{You2026_23190,
  author = {You, Yuhuan and Qian, Yufan and Qu, Tianshu and Wang, Bin and Lv, Xueyang},
  title = {{Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching}},
  pages = {10293:1-},
  year = {2026},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23190}
}

TY  - CPAPER
TI  - Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching
AU  - You, Yuhuan
AU  - Qian, Yufan
AU  - Qu, Tianshu
AU  - Wang, Bin
AU  - Lv, Xueyang
SP  - 1
M1  - Paper 10293
PY  - 2026
DA  - 2026/05/28
UR  - https://aes.org/publications/elibrary-page/?id=23190
PB  - Audio Engineering Society
LA  - en
AB  - Higher-Order Ambisonics (HOA) encoding from sparse, irregular microphone arrays remains a critical challenge for consumer spatial audio capture in immersive communication and XR. We propose Flow-HOA, a generative framework that jointly optimizes a multi-dimensional objective encompassing time-domain, spectral, and spatial fidelity while producing a deployable, time-invariant bank of Finite Impulse Response (FIR) encoding filters. Using conditional flow matching, the model learns to map a simple prior distribution to the target distribution of FIR filter coefficients. Training is guided by a composite loss that balances time-domain waveform fidelity, multi-resolution spectral consistency, sub-band energy preservation, and spatial directivity constraints. Objective evaluations on synthetically simulated data demonstrate improved performance over strong model-based baselines in both signal fidelity and spatial accuracy metrics. Subjective listening tests on real microphone array recordings further confirm that Flow-HOA yields higher overall sound quality with reduced artifacts, demonstrating generalization from synthetic training data to real-world capture conditions.
ER  -