SOTAVerified

Acoustic Scene Classification

The goal of acoustic scene classification is to classify a test recording into one of the provided predefined classes that characterizes the environment in which it was recorded.

Source: DCASE 2019 Source: DCASE 2018

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 91–100 of 132 papers

TitleStatusHype
Enhancing Sound Texture in CNN-Based Acoustic Scene Classification—0
Environmental sound analysis with mixup based multitask learning and cross-task fusion—0
Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations—0
Hierarchical learning for DNN-based acoustic scene classification—0
Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework—0
Improving Acoustic Scene Classification in Low-Resource Conditions—0
Incremental Learning of Acoustic Scenes and Sound Events—0
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling—0
Label Tree Embeddings for Acoustic Scene Classification—0
Environmental Sound Classification with Parallel Temporal-spectral Attention—0
Show:102550
← PrevPage 10 of 14Next →
All datasetsCochlSceneDCASE 2019 MobileTAU Urban Acoustic Scenes 2019TUT Acoustic Scenes 2017TUT Urban Acoustic Scenes 2018

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Audio Flamingo1:1 Accuracy0.83—Unverified
2Qwen-Audio1:1 Accuracy0.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Basic + Spectrum CorrectionAccuracy70.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Two-stage ensemble system1:1 Accuracy81.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Qwen-Audio1:1 Accuracy0.65—Unverified
#ModelMetricClaimedVerifiedStatus
1ERGL: event relational graph representation learningAcc78.1—Unverified