Audio-CAPTCHA with distinction between random phoneme sequences and words spoken by multi-speaker.
Michitomo YamaguchiHiroaki KikuchiPublished in: SMC (2017)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- broadcast news
- spoken words
- spontaneous speech
- speaker identification
- automatic transcription
- speech sounds
- prosodic features
- speech recognition systems
- conversational speech
- word recognition
- speech corpus
- speech signal
- acoustic features
- speaker dependent
- speech segments
- audio visual
- out of vocabulary
- spoken document retrieval
- spoken documents
- multimedia
- speech synthesis
- spoken language
- visual speech
- speaker recognition
- human language
- noisy environments
- speech retrieval
- audio stream
- speech recognizer
- speaker verification
- phoneme recognition
- language model
- keywords
- audio signals
- speaker independent
- pattern recognition
- mel frequency cepstral coefficients
- n gram
- visual information
- pseudorandom
- sequential patterns
- information retrieval
- human machine interaction