Audio Classification
Audio Classification是一种机器学习任务,旨在对音频信号进行识别和分类,将其归入不同的类别。该任务的核心目标是使机器能够自动区分各种类型的音频,如音乐、语音和环境声音,从而在音频处理和分析中发挥关键作用。通过精准的音频分类,可以提升音频检索、监控和内容管理系统的效率与准确性,具有重要的应用价值。
Audio Set
audiofolder
AudioSet
MBT (AS-500K training + Video)
Balanced Audio Set
EAT
BirdCLEF 2021
Common Voice 16.1
CREMA-D
DCASE
CrissCross (AudioSet)
DEEP-VOICE: DeepFake Voice Recognition
DiCOVA
EPIC-KITCHENS-100
Audiovisual Masked Autoencoder
(Audiovisual, Single)
EPIC-SOUNDS
ESC-50
InternVideo2
FSD50K
ICBHI Respiratory Sound Database
BTS
LSVSC
MeerKAT: Meerkat Kalahari Audio Transcripts
animal2vec
MNIST
Multimodal PISA
RAVDESS
SHD
SNN with Dilated Convolution with Learnable Spacings
Speech Commands
EAT
SSC
Event-SSM
UCR Time Series Classification Archive
CDIL
VGGSound
ONE-PEACE (Audio-Visual)
VocalSound
VocalSound Baseline