Count-Density Networks for Modal Plate Parameter Estimation

arXiv:2611.02083 · eess.AS · Submitted 2026-11-01 · Read on arXiv

eess.AS

Submitted: 2026-11-01

Updated: 2026-11-01

Comments: 3 pages, 1 figure, 1 table. DAFx26 Parameter Estimation Challenge, Task B. Code: https://github.com/davidmarttila/dafx_challenge

Journal ref: Proceedings of the 29th International Conference on Digital Audio Effects (DAFx26), Cambridge, MA, USA, pp. 585-587, 2026

Code: https://github.com/davidmarttila/dafx_challenge

License: http://creativecommons.org/licenses/by/4.0/

The gist: We describe two submissions to Task B of the 1st DAFx Parameter Estimation Challenge, which estimates an unknown number of modal frequency, decay…

Terminology

Abstract

We describe two submissions to Task B of the 1st DAFx Parameter Estimation Challenge, which estimates an unknown number of modal frequency, decay, and gain triples from a synthetic plate-reverb impulse response. The first method combines pooled spectral features with time-domain and absolute-scale conditioning in a real-valued convolutional count-density network, while the second uses a complex-valued Transformer count-density network. Both methods jointly infer the modal count and per-mode attributes directly from the IR. On an independently generated 100-IR comparison set, the two neural estimators achieve lower overall challenge error than the evaluated classical baselines, with frequency and decay estimation substantially more accurate than gain estimation.

Related papers