Learning General Audio Representations With Large-Scale Training of Patchout Audio Transformers.
Khaled KoutiniShahed MasoudianFlorian SchmidHamid Eghbal-zadehJan SchlüterGerhard WidmerPublished in: HEAR@NeurIPS (2021)
Keyphrases
- supervised learning
- learning systems
- learning process
- online training
- visual information
- special case
- inductive inference
- unsupervised learning
- learning stage
- learning speed
- cross modal
- recurrent networks
- small scale
- multimedia
- knowledge acquisition
- online learning
- active learning
- external representations
- mobile learning
- audio visual
- signal processing
- reinforcement learning