Matching Text and Audio Embeddings: Exploring Transfer-learning Strategies for Language-based Audio Retrieval.
Benno WeckMiguel Pérez FernándezHolger KirchhoffXavier SerraPublished in: CoRR (2022)
Keyphrases
- learning strategies
- human language
- text graphics
- multimedia information
- multimedia
- audio content
- spoken documents
- text to speech
- information retrieval
- cross modal
- audio visual content
- active learning
- online learning
- information retrieval systems
- audio visual
- cross media
- keywords
- text retrieval
- multimedia databases
- video search
- visual information
- natural language
- image retrieval
- english text
- relevance feedback
- multimedia documents
- string matching
- language learning
- blended learning
- multimedia data
- vector space
- query expansion
- machine learning