New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer.
Javier LatorreKoji IwanoSadaoki FuruiPublished in: Speech Commun. (2006)
Keyphrases
- speech recognition
- text to speech
- hidden markov models
- automatic speech recognition
- speaker recognition
- audio visual
- prosodic features
- speaker verification
- speaker identification
- speech signal
- speech synthesis
- noisy environments
- speaker diarization
- automatic speech recognition systems
- vocal tract
- speaker dependent
- gaussian mixture model
- visual speech
- feature selection
- phoneme recognition
- data sets
- acoustic features
- language model
- speech recognition systems
- speaker independent
- audio stream