Low computational cost speech synthesis based on deep neural networks using hidden semi-Markov model structures.
Motoki ShimadaKei HashimotoKeiichiro OuraYoshihiko NankakuKeiichi TokudaPublished in: SSW (2019)
Keyphrases
- speech synthesis
- computational cost
- neural network
- speech recognition
- text to speech
- pattern recognition
- vocal tract
- fuzzy logic
- neural network model
- hidden semi markov models
- back propagation
- artificial neural networks
- hidden markov models
- abnormality detection
- prosodic features
- complex systems
- anomaly detection
- network architecture
- low cost
- computer vision