Active Speech Obscuration with Speaker-dependent Human Speech-like Noise for Speech Privacy.
Yoshitaka OhshioHaruka AdachiKenta IwaiTakanobu NishiuraYoichi YamashitaPublished in: APSIPA (2018)
Keyphrases
- speech recognition
- speaker dependent
- speaker identification
- phoneme recognition
- speech recognizer
- noisy environments
- text to speech
- automatic speech recognition
- speech signal
- broadcast news
- spoken language
- speaker independent
- speech synthesis
- feature extraction
- emotional state
- audio visual
- pattern recognition
- video search
- speaker recognition
- generative model
- spectral features
- multi modal
- hidden markov models
- bayesian networks
- machine learning