Table 9 Details of ASVspoof 2019 physical access corpus
From: Discriminative features based on modified log magnitude spectrum for playback speech detection
Subset | # Speakers | # Utterances | ||
|---|---|---|---|---|
| Â | Male | Female | Bonafide | Spoof |
Training | 8 | 12 | 5400 | 48,600 |
Development | 8 | 12 | 5400 | 24,300 |
Evaluation | 30 | 37 | 18,089 | 13,4630 |