BAST: Binaural Audio Spectrogram Transformer for Binaural Sound Localization.
Sheng KuangKiki van der HeijdenSiamak MehrkanoonPublished in: CoRR (2022)
Keyphrases
- sound source
- speech signal
- audio features
- localization algorithm
- environmental sounds
- audio visual
- single channel
- transfer function
- speaker identification
- acoustic features
- fuzzy logic
- visual information
- speech recognition
- visual data
- fault diagnosis
- multimedia
- multi modal
- wavelet transform
- automatic speech recognition
- non stationary
- audio signal
- accurate localization
- power transformers
- localization method
- neural network
- audio signals
- pattern recognition
- expert systems
- pattern analysis
- signal processing