VAB-Encodec (Ours)

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio2 results

Audio GenerationonClassical music, 5 seconds at 12 kHz
Bits per byte· 2024-09-27
40
SOTA
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation arXiv:2409.19132
Audio ClassificationonAudio Set
Mean AP· 2024-09-27
38.7
best: 48.5 (M2D-AS/0.7)
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation arXiv:2409.19132

Methodology1 result

ClassificationonAudio Set
Mean AP· 2024-09-27
38.7
best: 48.5 (M2D-AS/0.7)
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation arXiv:2409.19132