Matching Text and Audio Embeddings: Exploring Transfer-Learning Strategies for Language-Based Audio Retrieval.
Benno WeckMiguel Pérez FernándezHolger KirchhoffXavier SerraPublished in: DCASE (2022)
Keyphrases
- learning strategies
- human language
- audio content
- text graphics
- multimedia information
- information retrieval
- multimedia
- cross modal
- text to speech
- spoken documents
- text retrieval
- audio visual
- visual information
- online learning
- active learning
- audio visual content
- multimedia documents
- natural language
- multimedia databases
- data mining
- string matching
- keywords
- query expansion
- audio features
- multimedia data
- language generation
- information retrieval systems
- english text
- blended learning
- cross media
- music information retrieval
- test collection
- mental models