AST: Audio Spectrogram Transformer.
Yuan GongYu-An ChungJames R. GlassPublished in: Interspeech (2021)
Keyphrases
- multimedia
- signal processing
- pattern analysis
- fuzzy logic
- audio video
- power system
- visual data
- visual information
- audio visual
- speech signal
- music score
- speaker identification
- audio stream
- multimedia information
- audio features
- audio signals
- data sets
- wigner distribution
- digital audio
- energy distribution
- automatic transcription
- power transformers
- single channel
- emotion recognition
- noise model
- multi channel
- pattern recognition