Self-supervised audio models are typically pre-trained on large collections of real-world recordings, and the resulting representations may be shaped by the acoustic coverage, recording conditions, and dataset-specific correlations of the source corpus. We investigate whether procedurally generated audio can provide a...
Feng-Rui Liu, Rui-Yang Huang, Qi-Jian Zheng et al.· IEEE Transactions on Audio,...· 2 citations
DSR is introduced, a causal post-selection operator that repairs destination support without retraining the host predictor or increasing the maintained set size, and shows that finite-set support allocation is a useful prediction-side control point when a fixed hypothesis set serves as the interface to downstream syste...
Feng-Rui Liu, Jia-Jun Peng, Duo Peng et al.· 0 citations
Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points.
Feng-Rui Liu, Ning Shen, Yi Li et al.· arXiv.org· 0 citations
Procedural audio has emerged as a viable source for transferable audio representation learning, but its design principles remain unclear.We revisit two questions: how a procedural source should be scaled, and whether training choices developed on natural audio should transfer unchanged to procedural data.Using a contro...
Jia-Jun Peng, Feng-Rui Liu, Xin-Yu Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.