Central to our contribution is TexStat, a loss function grounded in au- ditory perception and statistical modeling

CONCLUSIONS This paper introduced a novel framework for advancing the analysis, synthesis of texture sounds through deep learning · 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

citation-role summary

method 1

use method 1

cs.SD · 2025-06-04 · conditional · novelty 6.0

TexStat is a differentiable, perception-inspired loss and evaluation metric for texture sounds, demonstrated with a new DDSP-based synthesizer.

Showing 1 of 1 citing paper.

A Statistics-Driven Differentiable Approach for Sound Texture Synthesis and Analysis cs.SD · 2025-06-04 · conditional · none · ref 6
TexStat is a differentiable, perception-inspired loss and evaluation metric for texture sounds, demonstrated with a new DDSP-based synthesizer.