ATST: Audio Representation Learning with Teacher-Student Transformer
Open paper
Benchmark
Model
Rank
Results
audio-classification-on-balanced-audio-set
Base (ours)
#5
Mean AP: 37.4
speaker-identification-on-voxceleb1
ATST Base (ours)
#6
Top-1 (%): 94.3
Accuracy: 94.3
Rank counts only results with a code link.