Pitch adaptive training for hmm-based singing voice synthesis.
Keiichiro OuraAyami MaseYoshihiko NankakuKeiichi TokudaPublished in: ICASSP (2012)
Keyphrases
- hidden markov models
- fundamental frequency
- training examples
- program synthesis
- supervised learning
- training phase
- neural network
- case study
- multiscale
- test set
- voice activity detection
- database
- acoustic features
- adaptive systems
- texture synthesis
- character recognition
- training samples
- training set
- high level
- information systems
- genetic algorithm