Skip to content
Open access

CATF-Net: Content-Adaptive Multi-View Time–Frequency Fusion for Pretraining-Free Classification Across Heterogeneous Audio Tasks

2026 · IEEE Access · Vol 14, pp. 165915-165930 · 0 citations · 47 references

Abstract

Audio classification across speech-command and environmental-sound tasks requires both fine temporal cues and structured spectral context, yet many high-performing systems rely on external pretraining. We propose CATF-Net, a supervised framework trained from random initialization using only the labeled training data of each target benchmark. CATF-Net first learns sample-dependent weights over Mel, log-magnitude, and phase-derived spectral views and then combines the resulting spectral embedding with a raw-waveform temporal embedding through branch-wise regularization and parameter-free addition. The shared spectral interface also permits alternative descriptors to be incorporated without changing the temporal branch. The dataset-specific configurations contain 15.61–21.23 M parameters, compared with 81–90 M for several pretrained baselines considered in our experiments. CATF-Net achieves 92.95%, 98.50%, 86.49%, and 98.37% accuracy on ESC-50, ESC-10, UrbanSound8K, and Speech Commands V2, respectively, under their corresponding benchmark protocols.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.