Spoken-Text-Style Transfer with Conditional Variational Autoencoder and Content Word Storage.
Daiki YoshiokaYusuke YasudaNoriyuki MatsunagaYamato OhtaniTomoki TodaPublished in: INTERSPEECH (2022)
Keyphrases
- spoken documents
- writing style
- punctuation marks
- text content
- textual content
- keywords
- text information
- concept space
- semantic information
- page layout
- conversational speech
- content and structure
- text corpus
- semantic content
- spoken document retrieval
- sentence level
- scientific papers
- english text
- text mining
- related words
- english words
- related documents
- linguistic information
- natural language text
- text input
- textual information
- web documents
- metadata
- document content
- printed documents
- text queries
- lexical features
- multimedia
- word counts
- handwritten documents
- string matching
- n gram
- text retrieval
- image segmentation
- multiword
- co occurrence
- web pages
- textual descriptions
- authorship attribution
- multimedia documents
- web images
- compressed text
- character recognition
- word sense disambiguation
- multimedia content
- text documents