How can you use disfluencies and still sound as a good speaker?
Helena MonizAna Isabel MataIsabel TrancosoCéu VianaPublished in: INTERSPEECH (2008)
Keyphrases
- automatic speech recognition
- acoustic features
- speech recognition
- speaker verification
- speaker recognition
- speech signal
- spontaneous speech
- automatic speech recognition systems
- speaker identification
- sound source
- hidden markov models
- real world
- vector quantization
- multi agent
- information systems
- speaker diarization
- neural network