Mixed excitation for HMM-based speech synthesis.
Takayoshi YoshimuraKeiichi TokudaTakashi MasukoTakao KobayashiTadashi KitamuraPublished in: INTERSPEECH (2001)
Keyphrases
- expert systems
- speech synthesis
- speech recognition
- hidden markov models
- text to speech
- vocal tract
- prosodic features
- artificial intelligence
- speech corpus
- artificial neural networks
- multiscale
- face recognition
- neural network
- evolutionary algorithm
- language model
- pattern recognition
- image coding
- automatic speech recognition
- radio frequency
- machine learning
- data sets