Impacts of input linguistic feature representation on Japanese end-to-end speech synthesis.
Takato FujimotoKei HashimotoKeiichiro OuraYoshihiko NankakuKeiichi TokudaPublished in: SSW (2019)
Keyphrases
- end to end
- feature representation
- speech synthesis
- speech recognition
- text to speech
- feature representations
- feature extraction
- face recognition
- admission control
- low dimensional
- input data
- congestion control
- feature set
- neural network
- sparse representation
- information retrieval
- machine learning
- feature descriptors
- application layer
- feature vectors
- data sets