Speaker-independent style conversion for HMM-based expressive speech synthesis.
Hiroki KanagawaTakashi NoseTakao KobayashiPublished in: ICASSP (2013)
Keyphrases
- speech synthesis
- speech recognition
- speaker independent
- hidden markov models
- speaker dependent
- vocal tract
- prosodic features
- speech recognizer
- language model
- speech signal
- automatic speech recognition
- speech recognition systems
- noisy environments
- acoustic models
- speaker identification
- pattern recognition
- speaker adaptation
- information retrieval
- machine learning
- classification accuracy
- computer vision