When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition.
Shu WangJiahao CaoXu HeKun SunQi LiPublished in: CCS (2020)
Keyphrases
- frequency domain
- automatic speech recognition
- spatial domain
- speech recognition
- fourier transform
- speech signal
- power spectrum
- hidden markov models
- cross correlation
- conversational speech
- speech retrieval
- subband
- feature extraction
- word error rate
- power spectra
- denoising
- noisy environments
- frequency analysis
- broadcast news
- spectrum analysis
- fast fourier transform
- multiresolution
- fourier analysis
- noisy images
- discrete fourier transform
- pattern recognition
- watermarking algorithm
- machine learning