id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
bracis-33571	Virgilli, Rafaello; Candido Junior, Arnaldo; Rosa, Augusto Seben da; Oliveira, Frederico S.; Soares, Anderson da Silva	Dual-Bandwidth Spectrogram Analysis for Speaker Verification	2024		.htm	text/html	4922	257	42	The average training duration was 1.8 h per epoch for single spectrogram models and 2.21 h for dual-bandwidth spectrogram models. This sums to 360 h for single spectrogram models and 442 h for dual-bandwidth models.	cache/bracis-33571.htm	txt/bracis-33571.txt