Segmental Pitch Control Using Speech Input Based on Differential Contexts and Features for Customizable Neural Speech Synthesis.
Shinya HanabusaTakashi NoseAkinori ItoPublished in: IIH-MSP (2) (2018)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- vocal tract
- information retrieval
- hidden markov models
- feature extraction
- neural network
- feature vectors
- co occurrence
- input features
- speech corpus
- speech recognition systems
- network architecture
- speaker identification
- emotion recognition
- extracted features
- neural classifier
- image features
- feature space