Predicting VQVAE-based Character Acting Style from Quotation-Annotated Text for Audiobook Speech Synthesis.
Wataru NakataTomoki KoriyamaShinnosuke TakamichiYuki SaitoYusuke IjimaRyo MasumuraHiroshi SaruwatariPublished in: INTERSPEECH (2022)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- writing style
- vocal tract
- text retrieval
- manually constructed
- prosodic features
- authorship attribution
- text recognition
- scene text
- text input
- word processing
- text detection
- database
- free text
- text mining
- keywords
- handwritten characters
- text lines
- image coding
- text classification
- hidden markov models
- information retrieval
- printed text
- neural network