Speaker adaptation of pitch and spectrum for HMM-based speech synthesis.
Masatsune TamuraTakashi MasukoKeiichi TokudaTakao KobayashiPublished in: Systems and Computers in Japan (2004)
Keyphrases
- speech synthesis
- speech recognition
- speaker adaptation
- hidden markov models
- vocal tract
- speaker independent
- speech recognizer
- automatic speech recognition
- speaker dependent
- prosodic features
- speech signal
- language model
- speech recognition systems
- speaker identification
- pattern recognition
- acoustic features
- noisy environments
- text to speech
- character recognition
- natural language processing
- support vector machine
- probabilistic model
- feature vectors
- machine learning
- neural network