On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers.

Paul Primus Gerhard Widmer

Published in: CoRR (2023)

Keyphrases

video recordings
short time fourier transform
multimedia
pairwise
lifelog
signal processing
visual information
audio visual
image processing
low frequency
digital video
video sequences
visual data
speech signal
mobile terminals
wigner distribution