Speaker de-identification using diphone recognition and speech synthesis.
Tadej JustinVitomir StrucSimon DobrisekBostjan VesnicerIvo IpsicFrance MihelicPublished in: FG (2015)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- speech corpus
- vocal tract
- speaker independent
- text to speech
- handwriting recognition
- pattern recognition
- speaker dependent
- object recognition
- recognition rate
- recognition accuracy
- automatic speech recognition
- image recognition
- noisy environments
- hidden markov models
- feature extraction
- speech sounds
- face recognition
- speaker identification
- recognition algorithm
- word recognition
- speaker diarization
- automatic recognition
- visual recognition
- speech signal
- character recognition
- image processing