Name
Title | ||
|---|---|---|
Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge |
Abstract | ||
|---|---|---|
•Employing Constant Q Cepstral Coefficient (CQCC) features to represent each spoof and genuine sample.•Using Variational AutoEncoders (VAEs) to transform the extracted CQCC from sparce feature space to latent feature space and compress them to more informative and compressed vectors.•Using Siamese Network for the first time to classify the samples based on compressed features from VAE bottleneck.•Improving the performance in terms of EER by 10% and t-DCF by 20%, in comparison with baseline system. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.csl.2020.101105 | Computer Speech & Language |
Keywords | DocType | Volume |
Spoof detection,Replay attack,ASVspoof challenge,CQCC,Autoencoder,Siamese network | Journal | 64 |
ISSN | Citations | PageRank |
0885-2308 | 2 | 0.55 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mohammad Adiban | 1 | 2 | 1.91 |
| Hossein Sameti | 2 | 229 | 41.40 |
| Saeedreza Shehnepoor | 3 | 21 | 2.98 |