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 131–132 of 132 papers
All datasetsCochlSceneDCASE 2019 MobileTAU Urban Acoustic Scenes 2019TUT Acoustic Scenes 2017TUT Urban Acoustic Scenes 2018
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Audio Flamingo | 1:1 Accuracy | 0.83 | — | Unverified |
| 2 | Qwen-Audio | 1:1 Accuracy | 0.8 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Basic + Spectrum Correction | Accuracy | 70.4 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Two-stage ensemble system | 1:1 Accuracy | 81.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Qwen-Audio | 1:1 Accuracy | 0.65 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ERGL: event relational graph representation learning | Acc | 78.1 | — | Unverified |