Can We Use Speaker Recognition Technology to Attack Itself? Enhancing Mimicry Attacks Using Automatic Target Speaker Selection.
Tomi KinnunenRosa González HautamäkiVille VestmanMd. SahidullahPublished in: ICASSP (2019)
Keyphrases
- speaker recognition
- gaussian mixture model
- speaker verification
- countermeasures
- vector quantization
- probabilistic neural network
- speaker identification
- ddos attacks
- speech signal
- speech recognition
- noisy environments
- audio visual
- maximum likelihood
- multi modal
- gaussian process regression
- mel frequency cepstral coefficients