AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition.
Mohamad FakihRouwaida KanjFadi J. KurdahiMohammed E. FoudaPublished in: CoRR (2023)
Keyphrases
- speech recognition
- cross domain
- language model
- speech synthesis
- knowledge transfer
- hidden markov models
- transfer learning
- automatic speech recognition
- sentiment classification
- speech recognizer
- text categorization
- speech recognition technology
- pattern recognition
- speech recognition systems
- speaker identification
- speech signal
- target domain
- noisy environments
- information extraction
- bayesian networks
- decision trees
- machine learning