Audio Classification

Audio Classification is a machine learning task that involves identifying and tagging audio signals into different classes or categories. The goal of audio classification is to enable machines to automatically recognize and distinguish between different types of audio, such as music, speech, and environmental sounds.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–25 of 361 papers

Title	Date	Tasks	Status	Hype	Score
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding	Mar 22, 2024	Action ClassificationAction Recognition	CodeCode Available	7	5
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment	Oct 3, 2023	Audio ClassificationContrastive Learning	CodeCode Available	4	5
EAT: Self-Supervised Pre-Training with Efficient Audio Transformer	Jan 7, 2024	Audio ClassificationSelf-Supervised Learning	CodeCode Available	3	5
CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification	Mar 13, 2022	Audio ClassificationKnowledge Distillation	CodeCode Available	3	5
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities	May 18, 2023	1 Image, 2*2 StitchiAction Classification	CodeCode Available	3	5
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models	Nov 14, 2023	Acoustic Scene ClassificationAudio captioning	CodeCode Available	3	5
Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics	Apr 25, 2024	Audio ClassificationTransfer Learning	CodeCode Available	3	5
SSAST: Self-Supervised Audio Spectrogram Transformer	Oct 19, 2021	Audio ClassificationClassification	CodeCode Available	2	5
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model	May 20, 2024	Audio ClassificationGPU	CodeCode Available	2	5
Benchmarking Representations for Speech, Music, and Acoustic Events	May 2, 2024	Audio ClassificationBenchmarking	CodeCode Available	2	5
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning	Jun 5, 2024	Audio ClassificationClassification	CodeCode Available	2	5
BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics	Mar 15, 2024	Audio ClassificationClassification	CodeCode Available	2	5
Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio	Feb 14, 2024	Audio ClassificationDecoder	CodeCode Available	2	5
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition	Jan 4, 2024	AttributeAudio Classification	CodeCode Available	2	5
Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models	Jan 16, 2023	Audio ClassificationFew-Shot Learning	CodeCode Available	2	5
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation	Nov 9, 2022	Audio ClassificationAudio Tagging	CodeCode Available	2	5
Global birdsong embeddings enable superior transfer learning for bioacoustic classification	Jul 12, 2023	Audio ClassificationDecision Making	CodeCode Available	2	5
AST: Audio Spectrogram Transformer	Apr 5, 2021	Audio ClassificationAudio Tagging	CodeCode Available	2	5
Contrastive Audio-Visual Masked Autoencoder	Oct 2, 2022	Audio ClassificationAudio Tagging	CodeCode Available	2	5
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models	Oct 24, 2023	Audio ClassificationAudio Tagging	CodeCode Available	2	5
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection	Feb 2, 2022	Audio ClassificationEvent Detection	CodeCode Available	2	5
CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition	Oct 18, 2023	Audio ClassificationContrastive Learning	CodeCode Available	1	5
Audio classification with Dilated Convolution with Learnable Spacings	Sep 25, 2023	Audio ClassificationAudio Tagging	CodeCode Available	1	5
Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks	Jan 6, 2022	Audio ClassificationClassification	CodeCode Available	1	5
Adaptive Differential Denoising for Respiratory Sounds Classification	Jun 3, 2025	Audio ClassificationClassification	CodeCode Available	1	5

Show:10 25 50

← PrevPage 1 of 15Next →

All datasets AudioSet ESC-50 ICBHI Respiratory Sound Database VGGSound SHD FSD50K Balanced Audio Set Speech Commands SSC BirdCLEF 2021 DCASE EPIC-KITCHENS-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	OmniVec2	Test mAP	0.56	—	Unverified
2	OmniVec	Test mAP	0.55	—	Unverified
3	EquiAV	Test mAP	0.55	—	Unverified
4	MAViL (Audio-Visual, single)	Test mAP	0.53	—	Unverified
5	Audiovisual Masked Autoencoder (Audiovisual, Single)	Test mAP	0.52	—	Unverified
6	CAV-MAE (Audio-Visual)	Test mAP	0.51	—	Unverified
7	BEATs (Audio-only, Ensemble)	Test mAP	0.51	—	Unverified
8	UAVM (Audio + Video)	Test mAP	0.5	—	Unverified
9	SSLAM (Audio-Only, Single)	Test mAP	0.5	—	Unverified
10	mn40_as (Ensemble)	Test mAP	0.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OmniVec2	Top-1 Accuracy	99.1	—	Unverified
2	InternVideo2	Top-1 Accuracy	98.6	—	Unverified
3	M2D2 AS+	Top-1 Accuracy	98.5	—	Unverified
4	OmniVec	Top-1 Accuracy	98.4	—	Unverified
5	BEATs	Top-1 Accuracy	98.1	—	Unverified
6	mn40_as	Top-1 Accuracy	97.45	—	Unverified
7	M2D-CLAP/0.7	Top-1 Accuracy	97.4	—	Unverified
8	DyMN-L	Top-1 Accuracy	97.4	—	Unverified
9	M2D-AS/0.7	Top-1 Accuracy	97.2	—	Unverified
10	HTS-AT	Top-1 Accuracy	97	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ADD	ICBHI Score	65.53	—	Unverified
2	BEATs (PAFA)	ICBHI Score	64.84	—	Unverified
3	BTS	ICBHI Score	63.54	—	Unverified
4	BEATs (CE)	ICBHI Score	63.49	—	Unverified
5	M2D-X/0.7 (η=0.3)	ICBHI Score	63.29	—	Unverified
6	CycleGuardian	ICBHI Score	63.26	—	Unverified
7	M2D/0.7 (e=0.3)	ICBHI Score	62.73	—	Unverified
8	Audio-CLAP	ICBHI Score	62.56	—	Unverified
9	AST (Patch-Mix CL)	ICBHI Score	62.37	—	Unverified
10	AFT on Mixed-500	ICBHI Score	61.79	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MBT (AV)	Top 5 Accuracy	85.6	—	Unverified
2	Mirasol3B	Top 1 Accuracy	69.8	—	Unverified
3	CA2ST(B/16)	Top 1 Accuracy	68.3	—	Unverified
4	ONE-PEACE (Audio-Visual)	Top 1 Accuracy	68.2	—	Unverified
5	CAVA(B/16)	Top 1 Accuracy	68.2	—	Unverified
6	EquiAV	Top 1 Accuracy	67.1	—	Unverified
7	MAViL	Top 1 Accuracy	67.1	—	Unverified
8	MMT (Audio-Visual)	Top 1 Accuracy	66.2	—	Unverified
9	CAV-MAE (Audio-Visual)	Top 1 Accuracy	65.9	—	Unverified
10	UAVM (Audio + Video)	Top 1 Accuracy	65.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Event-SSM	Percentage correct	95.9	—	Unverified
2	SNN with Dilated Convolution with Learnable Spacings	Percentage correct	95.1	—	Unverified
3	SNN featuring learnable axonal delays with adaptively delay caps	Percentage correct	92.45	—	Unverified
4	CNN	Percentage correct	92.4	—	Unverified
5	SNN with spatio-temporal filters and attention	Percentage correct	92.4	—	Unverified
6	SNN with temporal-wise attention	Percentage correct	91.1	—	Unverified
7	SNN	Percentage correct	87	—	Unverified
8	Recurrent convolutional SNN	Percentage correct	83.5	—	Unverified
9	Recurrent SNN	Percentage correct	83.2	—	Unverified
10	Sparse Spiking Gradient Descent	Percentage correct	77.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ONE-PEACE	mAP	69.7	—	Unverified
2	MN	mAP	65.6	—	Unverified
3	PaSST-S	mAP	65.55	—	Unverified
4	DyMN-L	mAP	65.5	—	Unverified
5	PaSST-N-S	mAP	64.2	—	Unverified
6	LHGNN	Mean AP	59	—	Unverified
7	PSLA	mAP	56.71	—	Unverified
8	MATPAC (SSL Model)	mAP	55.2	—	Unverified
9	Temporal Knowledge Distillation for On-device Audio Classification	mAP	54.8	—	Unverified
10	Large 6-Layer Transformer with Pooling	mAP	53.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EquiAV	Mean AP	42.4	—	Unverified
2	SSLAM	Mean AP	40.9	—	Unverified
3	EAT	Mean AP	40.3	—	Unverified
4	BEATs	Mean AP	38.9	—	Unverified
5	Base (ours)	Mean AP	37.4	—	Unverified
6	SSAST-PATCH	Mean AP	31	—	Unverified
7	SSAST-FRAME	Mean AP	29.2	—	Unverified
8	Conformer	Mean AP	27.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PDC	Accuracy	97.8	—	Unverified
2	ASM-RH	Accuracy	96.51	—	Unverified
3	EfficientLEAF	Accuracy	95.2	—	Unverified
4	melspect	Accuracy	95.1	—	Unverified
5	LEAF	Accuracy	95.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Event-SSM	Accuracy	88.4	—	Unverified
2	SNN with Dilated Convolution with Learnable Spacings	Accuracy	80.69	—	Unverified
3	RadLIF	Accuracy	77.4	—	Unverified
4	SpikGRU	Accuracy	77	—	Unverified
5	Adaptive SRNN	Accuracy	74.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EfficientLEAF (8s)	Accuracy	72.2	—	Unverified
2	EfficientLEAF	Accuracy	42.9	—	Unverified
3	LEAF	Accuracy	42.3	—	Unverified
4	melspect	Accuracy	39.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CrissCross (AudioSet)	Top-1 Accuracy	97	—	Unverified
2	CrissCross (Kinetics-400)	Top-1 Accuracy	96	—	Unverified
3	XDC	Top-1 Accuracy	95	—	Unverified
4	CrissCross (Kinetics-Sound)	Top-1 Accuracy	93	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Audiovisual Masked Autoencoder (Audiovisual, Single)	Top-1 Action	46	—	Unverified
2	Audiovisual Masked Autoencoder (Video-only, Single)	Top-1 Action	45.8	—	Unverified
3	Audiovisual Masked Autoencoder (Audio-only, Single)	Top-1 Action	19.7	—	Unverified
4	PlayItBackX3	Top-1 Action	15.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	M2D-AS/0.7	Mean AP	48.5	—	Unverified
2	LHGNN	Mean AP	46.6	—	Unverified
3	VAB-Encodec (Ours)	Mean AP	38.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EfficientLEAF	Accuracy	60.2	—	Unverified
2	melspect	Accuracy	58.8	—	Unverified
3	LEAF	Accuracy	50.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AUCO ResNet	AUC	0.82	—	Unverified
2	DenseNet 201	AUC	0.6	—	Unverified
3	Inception ResNet V2	AUC	0.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mirasol3B	Accuracy	78.2	—	Unverified
2	CA2ST(B/16)	Accuracy	61	—	Unverified
3	CAVA(B/16)	Accuracy	60.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ASM-RH-A	Top-1 Accuracy	75.4	—	Unverified
2	ERANN-0-4	Top-1 Accuracy	74.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Qwen-Audio	Accuracy	92.89	—	Unverified
2	VocalSound Baseline	Accuracy	90.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	XGBoost (330)	Accuracy (10-fold)	99.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	animal2vec	AP	0.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Audio	Accuracy (%)	64.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CDIL	FruitFlies	97.09	—	Unverified