Differentiable Time-Frequency Scattering On GPU - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Differentiable Time-Frequency Scattering On GPU


Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales. It offers an idealized model of spectrotemporal receptive fields (STRF) in the primary auditory cortex, and thus may serve as a biological plausible surrogate for human perceptual judgments at the scale of isolated audio events. Yet, prior implementations of JTFS and STRF have remained outside of the standard toolkit of perceptual similarity measures and evaluation methods for audio generation. We trace this issue down to three limitations: differentiability, speed, and flexibility. In this paper, we present an implementation of time-frequency scattering in Python. Unlike prior implementations, ours accommodates NumPy, PyTorch, and TensorFlow as backends and is thus portable on both CPU and GPU. We demonstrate the usefulness of JTFS via three applications: unsupervised manifold learning of spectrotemporal modulations, supervised classification of musical instruments, and texture resynthesis of bioacoustic sounds.
Fichier principal
Vignette du fichier
DAFx20in22_paper_25.pdf (2.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03863423 , version 1 (23-11-2022)


  • HAL Id : hal-03863423 , version 1


John Muradeli, Cyrus Vahidi, Changhong Wang, Han Han, Vincent Lostanlen, et al.. Differentiable Time-Frequency Scattering On GPU. Digital Audio Effects Conference (DAFx), Sep 2022, Vienna, Austria. ⟨hal-03863423⟩
67 View
38 Download


Gmail Facebook X LinkedIn More