SOTAVerified

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

Showing 301350 of 361 papers

TitleStatusHype
An Ensemble of Convolutional Neural Networks for Audio Classification0
Private Speech Classification with Secure Multiparty Computation0
A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition0
Self-Supervised MultiModal Versatile NetworksCode0
A Deep Neural Network for Audio Classification with a Classifier Attention Mechanism0
Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data0
Microphone Array Based Surveillance Audio Classification0
A FRAMEWORK FOR ROBUSTNESS CERTIFICATION OF SMOOTHED CLASSIFIERS USING F-DIVERGENCES0
Automatic Classification of Large-Scale Respiratory Sound Dataset Based on Convolutional Neural Network0
Exploring Context, Attention and Audio Features for Audio Visual Scene-Aware Dialog0
Leveraging Topics and Audio Features with Multimodal Attention for Audio Visual Scene-Aware Dialog0
Data augmentation approaches for improving animal audio classification0
Environmental Sound Classification with Parallel Temporal-spectral Attention0
Audiogmenter: a MATLAB Toolbox for Audio Data AugmentationCode0
LungBRN: A Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning AlgorithmCode0
Self-Supervised Learning by Cross-Modal Audio-Video ClusteringCode0
An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy0
Cross-modal supervised learning for better acoustic representationsCode0
Segment Relevance Estimation for Audio Analysis and Weakly-Labelled Classification0
Label-efficient audio classification through multitask learning and self-supervision0
The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks0
SpectroBank: A filter-bank convolutional layer for CNN-based audio applications0
Certifying Neural Network Audio Classifiers0
Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks0
AI for Earth: Rainforest Conservation by Acoustic Surveillance0
Universal Adversarial Audio PerturbationsCode0
Compact Global Descriptor for Neural NetworksCode0
Deep Neural Baselines for Computational Paralinguistics0
On the performance of residual block design alternatives in convolutional neural networks for end-to-end audio classification0
Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical BayesCode0
Simultaneously Learning Architectures and Features of Deep Neural Networks0
CNN depth analysis with different channel inputs for Acoustic Scene Classification0
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set RecognitionCode0
Zero-Shot Audio Classification Based on Class Label Embeddings0
A Robust Approach for Securing Audio Classification Against Adversarial Attacks0
Audio-Visual Model Distillation Using Acoustic ImagesCode0
Audio Classification of Bit-Representation Waveform0
Improving performance and inference on audio classification tasks using capsule networks0
Context, Attention and Audio Feature Explorations for Audio Visual Scene-Aware Dialog0
Cross-domain Deep Feature Combination for Bird Species Classification with Audio-visual Data0
AclNet: efficient end-to-end audio classification CNN0
Ubicoustics: Plug-and-Play Acoustic Activity RecognitionCode0
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization0
A Closer Look at Weak Label Learning for Audio EventsCode0
Multi-level Attention Model for Weakly Supervised Audio ClassificationCode0
Masked Conditional Neural Networks for Audio ClassificationCode0
WSNet: Learning Compact and Efficient Networks with Weight Sampling0
Representations of Sound in Deep Learning of Audio Features from Music0
Raw Waveform-based Audio Classification Using Sample-level CNN Architectures0
Learning Sparse Adversarial Dictionaries For Multi-Class Audio Classification0
Show:102550
← PrevPage 7 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OmniVec2Test mAP0.56Unverified
2OmniVecTest mAP0.55Unverified
3EquiAVTest mAP0.55Unverified
4MAViL (Audio-Visual, single)Test mAP0.53Unverified
5Audiovisual Masked Autoencoder (Audiovisual, Single)Test mAP0.52Unverified
6CAV-MAE (Audio-Visual)Test mAP0.51Unverified
7BEATs (Audio-only, Ensemble)Test mAP0.51Unverified
8UAVM (Audio + Video)Test mAP0.5Unverified
9SSLAM (Audio-Only, Single)Test mAP0.5Unverified
10mn40_as (Ensemble)Test mAP0.5Unverified
#ModelMetricClaimedVerifiedStatus
1OmniVec2Top-1 Accuracy99.1Unverified
2InternVideo2Top-1 Accuracy98.6Unverified
3M2D2 AS+Top-1 Accuracy98.5Unverified
4OmniVecTop-1 Accuracy98.4Unverified
5BEATsTop-1 Accuracy98.1Unverified
6mn40_asTop-1 Accuracy97.45Unverified
7DyMN-LTop-1 Accuracy97.4Unverified
8M2D-CLAP/0.7Top-1 Accuracy97.4Unverified
9M2D-AS/0.7Top-1 Accuracy97.2Unverified
10HTS-ATTop-1 Accuracy97Unverified
#ModelMetricClaimedVerifiedStatus
1ADDICBHI Score65.53Unverified
2BEATs (PAFA)ICBHI Score64.84Unverified
3BTSICBHI Score63.54Unverified
4BEATs (CE)ICBHI Score63.49Unverified
5M2D-X/0.7 (η=0.3)ICBHI Score63.29Unverified
6CycleGuardianICBHI Score63.26Unverified
7M2D/0.7 (e=0.3)ICBHI Score62.73Unverified
8Audio-CLAPICBHI Score62.56Unverified
9AST (Patch-Mix CL)ICBHI Score62.37Unverified
10AFT on Mixed-500ICBHI Score61.79Unverified
#ModelMetricClaimedVerifiedStatus
1MBT (AV)Top 5 Accuracy85.6Unverified
2Mirasol3BTop 1 Accuracy69.8Unverified
3CA2ST(B/16)Top 1 Accuracy68.3Unverified
4ONE-PEACE (Audio-Visual)Top 1 Accuracy68.2Unverified
5CAVA(B/16)Top 1 Accuracy68.2Unverified
6EquiAVTop 1 Accuracy67.1Unverified
7MAViLTop 1 Accuracy67.1Unverified
8MMT (Audio-Visual)Top 1 Accuracy66.2Unverified
9CAV-MAE (Audio-Visual)Top 1 Accuracy65.9Unverified
10UAVM (Audio + Video)Top 1 Accuracy65.8Unverified
#ModelMetricClaimedVerifiedStatus
1Event-SSMPercentage correct95.9Unverified
2SNN with Dilated Convolution with Learnable SpacingsPercentage correct95.1Unverified
3SNN featuring learnable axonal delays with adaptively delay capsPercentage correct92.45Unverified
4SNN with spatio-temporal filters and attentionPercentage correct92.4Unverified
5CNNPercentage correct92.4Unverified
6SNN with temporal-wise attentionPercentage correct91.1Unverified
7SNNPercentage correct87Unverified
8Recurrent convolutional SNNPercentage correct83.5Unverified
9Recurrent SNNPercentage correct83.2Unverified
10Sparse Spiking Gradient DescentPercentage correct77.5Unverified
#ModelMetricClaimedVerifiedStatus
1ONE-PEACEmAP69.7Unverified
2MNmAP65.6Unverified
3PaSST-SmAP65.55Unverified
4DyMN-LmAP65.5Unverified
5PaSST-N-SmAP64.2Unverified
6LHGNNMean AP59Unverified
7PSLAmAP56.71Unverified
8MATPAC (SSL Model)mAP55.2Unverified
9Temporal Knowledge Distillation for On-device Audio ClassificationmAP54.8Unverified
10Large 6-Layer Transformer with PoolingmAP53.7Unverified
#ModelMetricClaimedVerifiedStatus
1EquiAVMean AP42.4Unverified
2SSLAMMean AP40.9Unverified
3EATMean AP40.3Unverified
4BEATsMean AP38.9Unverified
5Base (ours)Mean AP37.4Unverified
6SSAST-PATCHMean AP31Unverified
7SSAST-FRAMEMean AP29.2Unverified
8ConformerMean AP27.6Unverified
#ModelMetricClaimedVerifiedStatus
1PDCAccuracy97.8Unverified
2ASM-RHAccuracy96.51Unverified
3EfficientLEAFAccuracy95.2Unverified
4LEAFAccuracy95.1Unverified
5melspectAccuracy95.1Unverified
#ModelMetricClaimedVerifiedStatus
1Event-SSMAccuracy88.4Unverified
2SNN with Dilated Convolution with Learnable SpacingsAccuracy80.69Unverified
3RadLIFAccuracy77.4Unverified
4SpikGRUAccuracy77Unverified
5Adaptive SRNNAccuracy74.2Unverified
#ModelMetricClaimedVerifiedStatus
1EfficientLEAF (8s)Accuracy72.2Unverified
2EfficientLEAFAccuracy42.9Unverified
3LEAFAccuracy42.3Unverified
4melspectAccuracy39.9Unverified
#ModelMetricClaimedVerifiedStatus
1CrissCross (AudioSet)Top-1 Accuracy97Unverified
2CrissCross (Kinetics-400)Top-1 Accuracy96Unverified
3XDCTop-1 Accuracy95Unverified
4CrissCross (Kinetics-Sound)Top-1 Accuracy93Unverified
#ModelMetricClaimedVerifiedStatus
1Audiovisual Masked Autoencoder (Audiovisual, Single)Top-1 Action46Unverified
2Audiovisual Masked Autoencoder (Video-only, Single)Top-1 Action45.8Unverified
3Audiovisual Masked Autoencoder (Audio-only, Single)Top-1 Action19.7Unverified
4PlayItBackX3Top-1 Action15.9Unverified
#ModelMetricClaimedVerifiedStatus
1M2D-AS/0.7Mean AP48.5Unverified
2LHGNNMean AP46.6Unverified
3VAB-Encodec (Ours)Mean AP38.7Unverified
#ModelMetricClaimedVerifiedStatus
1EfficientLEAFAccuracy60.2Unverified
2melspectAccuracy58.8Unverified
3LEAFAccuracy50.2Unverified
#ModelMetricClaimedVerifiedStatus
1AUCO ResNetAUC0.82Unverified
2DenseNet 201AUC0.6Unverified
3Inception ResNet V2AUC0.6Unverified
#ModelMetricClaimedVerifiedStatus
1Mirasol3BAccuracy78.2Unverified
2CA2ST(B/16)Accuracy61Unverified
3CAVA(B/16)Accuracy60.3Unverified
#ModelMetricClaimedVerifiedStatus
1ASM-RH-ATop-1 Accuracy75.4Unverified
2ERANN-0-4Top-1 Accuracy74.8Unverified
#ModelMetricClaimedVerifiedStatus
1Qwen-AudioAccuracy 92.89Unverified
2VocalSound BaselineAccuracy 90.5Unverified
#ModelMetricClaimedVerifiedStatus
1XGBoost (330)Accuracy (10-fold)99.3Unverified
#ModelMetricClaimedVerifiedStatus
1animal2vecAP0.91Unverified
#ModelMetricClaimedVerifiedStatus
1AudioAccuracy (%)64.5Unverified
#ModelMetricClaimedVerifiedStatus
1CDILFruitFlies97.09Unverified