Retrieval-Augmented Text-to-Audio Generation.
Yi YuanHaohe LiuXubo LiuQiushi HuangMark D. PlumbleyWenwu WangPublished in: CoRR (2023)
Keyphrases
- information retrieval
- text retrieval
- spoken documents
- text graphics
- audio content
- multimedia
- text generation
- multimedia documents
- multimedia search
- multimedia information
- semantic content
- retrieval engine
- cross media
- cross media retrieval
- audio visual content
- document analysis
- text to speech
- human language
- retrieval systems
- content based video retrieval
- search engine
- multimedia information retrieval
- document indexing
- video collections
- free text
- text indexing
- text mining
- lifelog
- image database
- user comments
- information retrieval systems
- cross modal
- test collection
- text collections
- conceptual retrieval
- query expansion
- keywords
- structured documents
- spoken document retrieval
- web documents
- multimedia databases
- textual information
- document retrieval
- retrieval model
- image retrieval
- relevance feedback
- natural language processing
- content based retrieval
- natural language generation
- document collections
- document content
- visual features
- content and structure
- semantic information
- music information retrieval