SSAST: Self-Supervised Audio Spectrogram Transformer.
Yuan GongCheng-I Jeff LaiYu-An ChungJames R. GlassPublished in: CoRR (2021)
Keyphrases
- multimedia
- pattern analysis
- fuzzy logic
- signal processing
- audio visual
- audio video
- fault diagnosis
- visual information
- audio files
- audio signals
- distribution network
- speech signal
- short time fourier transform
- energy distribution
- neural network
- text graphics
- music score
- audio recordings
- high voltage
- data sets
- audio stream
- video recordings
- cross modal
- digital video
- visual data
- computational intelligence
- pattern recognition
- artificial intelligence