uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures.
Afrina TabassumDung N. TranTrung DangIsmini LourentzouKazuhito KoishidaPublished in: ICASSP (2024)
Keyphrases
- multimedia
- audio visual
- audio files
- audio stream
- signal processing
- visual information
- digital audio
- digital video
- audio video
- multi modal
- music score
- mixture model
- audio signals
- music information retrieval
- audio recordings
- mixtures of gaussians
- speaker identification
- parameter settings
- unsupervised learning
- clustering algorithm