SSAST: Self-Supervised Audio Spectrogram Transformer.
Yuan GongCheng-I LaiYu-An ChungJames R. GlassPublished in: AAAI (2022)
Keyphrases
- multimedia
- pattern analysis
- fuzzy logic
- power system
- audio visual
- cross modal
- audio video
- signal processing
- fault diagnosis
- distribution network
- visual data
- music scores
- data sets
- wigner distribution
- power transformers
- emotion recognition
- visual information
- image processing
- low level
- energy distribution
- digital audio
- music score
- artificial intelligence
- genetic algorithm