Audio Classification
Audio Classification is a machine learning task aimed at recognizing and categorizing audio signals into different classes. The core objective of this task is to enable machines to automatically distinguish various types of audio, such as music, speech, and environmental sounds, thereby playing a crucial role in audio processing and analysis. Accurate audio classification can enhance the efficiency and accuracy of audio retrieval, monitoring, and content management systems, making it an important application.
AudioSet
MAViL (Audio-Visual, single)
ESC-50
BEATs
ICBHI Respiratory Sound Database
BTS
VGGSound
ONE-PEACE (Audio-Visual)
SHD
SNN with Dilated Convolution with Learnable Spacings
FSD50K
Balanced Audio Set
EquiAV
Speech Commands
EAT
DCASE
CrissCross (AudioSet)
SSC
Event-SSM
BirdCLEF 2021
EPIC-KITCHENS-100
Audiovisual Masked Autoencoder
(Audiovisual, Single)
Audio Set
CREMA-D
DiCOVA
RAVDESS
VocalSound
VocalSound Baseline
DEEP-VOICE: DeepFake Voice Recognition
EPIC-SOUNDS
MeerKAT: Meerkat Kalahari Audio Transcripts
animal2vec
Multimodal PISA
UCR Time Series Classification Archive
CDIL
audiofolder
Common Voice 16.1
LSVSC
MNIST