Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015) Database
Date
2018-11-28Author(s)
Unique identifier
http://dx.doi.org/10.7488/ds/298Metadata
Show full item recordResearch data
Citation
Tomi Kinnunen, University of Eastern Finland. Zhizheng Wu, University of Edinburgh. Nicholas Evans, EURECOM. Junichi Yamagishi, University of Edinburgh. , Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015) Database, 2018, http://dx.doi.org/10.7488/ds/298.Licensed under
Abstract
The database has been used in the first Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015). Genuine speech is collected from 106 speakers (45 male, 61 female) and with no significant channel or background noise effects. Spoofed speech is generated from the genuine data using a number of different spoofing algorithms. The full dataset is partitioned into three subsets, the first for training, the second for development and the third for evaluation. More details can be found in the evaluation plan in the summary paper.
The database has been used in the first Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015). Genuine speech is collected from 106 speakers (45 male, 61 female) and with no significant channel or background noise effects. Spoofed speech is generated from the genuine data using a number of different spoofing algorithms. The full dataset is partitioned into three subsets, the first for training, the second for development and the third for evaluation. More details can be found in the evaluation plan in the summary paper.