Audio Classification On Esc 50

Metrics

Top-1 Accuracy

Results

Performance results of various models on this benchmark

Model Name	Top-1 Accuracy	Paper Title	Repository
AVID	89.2	Audio-Visual Instance Discrimination with Cross-Modal Agreement
mn40_as	97.45	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
M2D/0.7	96.0	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
M2D-CLAP/0.7	97.4	M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
BEATs	98.1	BEATs: Audio Pre-Training with Acoustic Tokenizers
OmniVec2	99.1	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
LHGNN	96.2	LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging	-
XDC	84.8	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
ERANN-2-5	96.1	ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition	-
ACDNet	87.1	Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices
OmniVec	98.4	OmniVec: Learning robust representations with cross modal sharing	-
Multi-Channel Audio Feature with CNN	89.5	-	-
Audio Spectrogram Transformer	95.7	AST: Audio Spectrogram Transformer
AVTS	82.3	Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization	-
SepTr + LeRaC	91.58	Learning Rate Curriculum
XDC	85.4	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
L3	79.3	Look, Listen and Learn
Multi-Format Contrastive	90.5	Multi-Format Contrastive Learning of Audio Representations	-
InternVideo2	98.6	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
DyMN-L	97.4	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models

0 of 27 row(s) selected.