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

Showing 1120 of 132 papers

TitleStatusHype
A Two-Stage Approach to Device-Robust Acoustic Scene ClassificationCode1
DCASENET: A joint pre-trained deep neural network for detecting and classifying acoustic scenes and eventsCode1
CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile ApplicationCode1
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data AugmentationCode1
SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional NetworksCode1
Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNsCode1
Receptive-field-regularized CNN variants for acoustic scene classificationCode1
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene ClassificationCode1
Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 ChallengeCode0
Improving Acoustic Scene Classification with City Features0
Show:102550
← PrevPage 2 of 14Next →

Benchmark Results

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