EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Number of speakers and the corresponding number of genuine and playback utterances in the training, development, and evaluation sets in ASVspoof 2017 V2

From: Discriminative features based on modified log magnitude spectrum for playback speech detection

Subset	Number
	Speakers	Utterances	Genuine	Spoofed
Training	10	3014	1507	1507
Development	8	1710	760	950
Evaluation	24	13,306	1298	12,008

Back to article page