SOTAVerified

Sound Event Detection

Sound Event Detection (SED) is the task of recognizing the sound events and their respective temporal start and end time in a recording. Sound events in real life do not always occur in isolation, but tend to considerably overlap with each other. Recognizing such overlapping sound events is referred as polyphonic SED.

Source: A report on sound event detection with different binaural features

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 126–150 of 194 papers

TitleStatusHype
DCASE 2024 Task 4: Sound Event Detection with Heterogeneous Data and Missing Labels—0
Deep Convolutional and Recurrent Networks for Polyphonic Instrument Classification from Monophonic Raw Audio Waveforms—0
DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection—0
DiffSED: Sound Event Detection with Denoising Diffusion—0
Divided spectro-temporal attention for sound event localization and detection in real scenes for DCASE2023 challenge—0
Do sound event representations generalize to other audio tasks? A case study in audio transfer learning—0
Dual Knowledge Distillation for Efficient Sound Event Detection—0
Effect of noise suppression losses on speech distortion and ASR performance—0
End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input—0
Energy Consumption Trends in Sound Event Detection Systems—0
Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall—0
Exploring the Potential of SSL Models for Sound Event Detection—0
Fine-Grained Engine Fault Sound Event Detection Using Multimodal Signals—0
FMSG-JLESS Submission for DCASE 2024 Task4 on Sound Event Detection with Heterogeneous Training Dataset and Potentially Missing Labels—0
Formula-Supervised Sound Event Detection: Pre-Training Without Real Data—0
Framework for evaluation of sound event detection in web videos—0
Frequency Dynamic Convolutions for Sound Event Detection—0
From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems—0
Leveraging Language Model Capabilities for Sound Event Detection—0
HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones—0
Impact of Noisy Labels on Sound Event Detection: Deletion Errors Are More Detrimental Than Insertion Errors—0
Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection—0
Impact of visual assistance for automated audio captioning—0
Improving Polyphonic Sound Event Detection on Multichannel Recordings with the Sørensen-Dice Coefficient Loss and Transfer Learning—0
Improving Sound Event Detection Metrics: Insights from DCASE 2020—0
Show:102550
← PrevPage 6 of 8Next →
All datasetsDESEDL3DAS21WildDESEDMivia Audio EventsMivia Road Events

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ATST-SEDevent-based F1 score63.4—Unverified
2SE-CRNN-16 with DualKDevent-based F1 score55.6—Unverified
3FDY-CRNNevent-based F1 score54—Unverified
4HTS-ATevent-based F1 score50.7—Unverified
5RCTevent-based F1 score49.62—Unverified
6FiltAug SEDevent-based F1 score49.6—Unverified
7SED-SSep baseline dcase task 4 2020 v2event-based F1 score40.7—Unverified
8Baseline dcase task 4 2020 v2event-based F1 score39—Unverified
9Baselineevent-based F1 score25.8—Unverified
10MAT-SEDPSDS10.59—Unverified
#ModelMetricClaimedVerifiedStatus
1PHC SEDnet n=8Error Rate0.56—Unverified
2Quaternion SEDnetError Rate0.52—Unverified
3PHC SEDnet n=16Error Rate0.51—Unverified
4PHC SEDnet n=4Error Rate0.45—Unverified
5PHC SEDnet n=2Error Rate0.39—Unverified
#ModelMetricClaimedVerifiedStatus
1CRNN (with BEATs + Separation)PSDS1 (-5dB)0.13—Unverified
2CRNN (with BEATs)PSDS1 (-5dB)0.07—Unverified
3CRNN (WildDESED + Curriculrm learning)PSDS1 (-5dB)0.05—Unverified
4CRNN (WildDESED)PSDS1 (-5dB)0.05—Unverified
5CRNNPSDS1 (-5dB)0.02—Unverified
#ModelMetricClaimedVerifiedStatus
1DENetRank-1 Recognition Rate0.98—Unverified
#ModelMetricClaimedVerifiedStatus
1DENetRank-1 Recognition Rate1—Unverified