GitHub

Beyond Spectrograms: Rethinking Audio Classification from EnCodec’s Latent Space

All the datasets must be located in the datasets folder. This folder should contain the following subfolders after downloading the datasets: GTZAN Speech_Music: Contains the GTZAN Speech Music dataset ...
NPR

All Songs Considered

February 13, 2026 • August Ponthier. Brent Faiyaz. Jill Scott's first album in more than a decade. NPR Music's Stephen Thompson is joined by Nastia Voynovskaya from KQED in San Francisco to chat about ...
NPR

New Music

February 17, 2026 • If you watch HBO’s The Pitt, you might have heard the gorgeous new song called “Need Someone” that Andrew Bird wrote for a recent episode. We’ve got that on this week’s show along ...
IEEE

FAST: Fast Audio Spectrogram Transformer

Abstract: In audio classification, developing efficient and robust models is critical for real-time applications. Inspired by the design principles of MobileViT, we present FAST (Fast Audio ...