Flap: Fast Language-Audio Pre-Training.
Ching-Feng YehPo-Yao HuangVasu SharmaShang-Wen LiGargi GoshPublished in: ASRU (2023)
Keyphrases
- training set
- human language
- supervised learning
- programming language
- language learning
- human mobility
- test set
- training phase
- training algorithm
- training examples
- visual information
- training process
- modeling language
- multimedia
- training samples
- neural network
- signal processing
- natural language
- audio visual
- training data
- audio video
- metadata