BEATs: Audio Pre-Training with Acoustic Tokenizers.
Sanyuan ChenYu WuChengyi WangShujie LiuDaniel TompkinsZhuo ChenWanxiang CheXiangzhan YuFuru WeiPublished in: ICML (2023)
Keyphrases
- feature extraction
- image classification
- feature vectors
- acoustic features
- audio signal
- training algorithm
- multimedia
- supervised learning
- neural network
- training process
- multi modal
- emotion recognition
- training phase
- data sets
- signal processing
- feature selection
- audio video
- discriminative training
- source localization
- prosodic features
- audio stream
- visual information
- test set
- online learning
- training set
- image sequences