# Acoustic Scene Classification on TUT Acoustic Scenes

Source: [Acoustic Scene Classification on TUT Acoustic Scenes](<https://www.sota2.com/research/sota/acoustic-scene-classification-on-tut-acoustic-scenes>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T12:38:15.022Z

Evaluation of Acoustic Scene Classification performance using the TUT Acoustic Scenes dataset, typically measured by Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Acoustic Scene Classification |
| Dataset (including any stated split) | TUT Acoustic Scenes |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 35 of 35 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/acoustic-scene-classification-on-tut-acoustic-scenes.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CNN14 | 67.54 | Not recorded | 68fa767a1e209131cea6d4ac |
| MobileNetV1 | 66.13 | Not recorded | 68fa767a1e209131cea6d4ac |
| HuBERT | 65.42 | Not recorded | 68fa767a1e209131cea6d4ac |
| ResNet38 | 65.34 | Not recorded | 68fa767a1e209131cea6d4ac |
| Wav2Vec 2.0 | 65.28 | Not recorded | 68fa767a1e209131cea6d4ac |
| Whisper | 65.14 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + CNN14 | 63.54 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + MobileNetV1 | 63.13 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + HuBERT | 62.42 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + ResNet38 | 62.34 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + Wav2Vec 2.0 | 62.28 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student + Whisper | 61.14 | Not recorded | 68fa767a1e209131cea6d4ac |
| Student Only | 58.13 | Not recorded | 68fa767a1e209131cea6d4ac |
| HLTDNN | 58.13 | Not recorded | 68fa767a1e209131cea6d4ac |
| ssLALM-2.8B | 35.9 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 33.3 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 33.2 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 32.8 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 32.8 | Not recorded | 68fa7b721e209131cea8883d |
| LTU-7B | 32.5 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 32.5 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 32.4 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 32.4 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 32 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 31.8 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 31.7 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 31.6 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 31.6 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 31.5 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 30.9 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 30.7 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-780M | 29.4 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-130M | 29.2 | Not recorded | 68fa7b721e209131cea8883d |
| SAM-2.7B | 27.7 | Not recorded | 68fa7b721e209131cea8883d |
| GAMA-7B | 21.5 | Not recorded | 68fa7b721e209131cea8883d |

### CNN14

Accuracy: 67.54. Result ID: 69c3d71c47f34ce924ad132d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"79.7M"}. This record does not assert independent reproduction.

### MobileNetV1

Accuracy: 66.13. Result ID: 69c3d71c47f34ce924ad132f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"4.3M"}. This record does not assert independent reproduction.

### HuBERT

Accuracy: 65.42. Result ID: 69c3d71c47f34ce924ad1331.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea26880.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/master/examples/hubert>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"95.7M"}. This record does not assert independent reproduction.

### ResNet38

Accuracy: 65.34. Result ID: 69c3d71c47f34ce924ad132e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"72.7M"}. This record does not assert independent reproduction.

### Wav2Vec 2.0

Accuracy: 65.28. Result ID: 69c3d71c47f34ce924ad1330.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68891e209131cea1cc36.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"95.0M"}. This record does not assert independent reproduction.

### Whisper

Accuracy: 65.14. Result ID: 69c3d71c47f34ce924ad1332.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Implementation](<https://github.com/openai/whisper>)

Recorded evaluation configuration: {"Model Type":"Teacher Model","# Parameters":"74.0M"}. This record does not assert independent reproduction.

### Student + CNN14

Accuracy: 63.54. Result ID: 69c3d71c47f34ce924ad130b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"CNN14","# Parameters (Student vs. Teacher)":"12.3K vs. 79.7M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student + MobileNetV1

Accuracy: 63.13. Result ID: 69c3d71c47f34ce924ad130d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"MobileNetV1","# Parameters (Student vs. Teacher)":"12.3K vs. 4.3M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student + HuBERT

Accuracy: 62.42. Result ID: 69c3d71c47f34ce924ad130f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"HuBERT","# Parameters (Student vs. Teacher)":"12.3K vs. 95.7M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student + ResNet38

Accuracy: 62.34. Result ID: 69c3d71c47f34ce924ad130c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"ResNet38","# Parameters (Student vs. Teacher)":"12.3K vs. 72.7M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student + Wav2Vec 2.0

Accuracy: 62.28. Result ID: 69c3d71c47f34ce924ad130e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"Wav2Vec 2.0","# Parameters (Student vs. Teacher)":"12.3K vs. 95.0M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student + Whisper

Accuracy: 61.14. Result ID: 69c3d71c47f34ce924ad1310.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"Teacher Model":"Whisper","# Parameters (Student vs. Teacher)":"12.3K vs. 74.0M","Adaptation Strategy":"Full teacher fine-tuning"}. This record does not assert independent reproduction.

### Student Only

Accuracy: 58.13. Result ID: 69c3d71c47f34ce924ad130a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

Recorded evaluation configuration: {"# Parameters":"11.3K"}. This record does not assert independent reproduction.

### HLTDNN

Accuracy: 58.13. Result ID: 69c3d71c47f34ce924ad132c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767a1e209131cea6d4ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70271e209131cea49735.md>)

Recorded evaluation configuration: {"Model Type":"Student Model","# Parameters":"11.3K"}. This record does not assert independent reproduction.

### ssLALM-2.8B

Accuracy: 35.9. Result ID: 69aa7e206dbb7075b953c6f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a16e.md>)

Recorded evaluation configuration: {"r":"8","Conn.":"Linear"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 33.3. Result ID: 69aa7e206dbb7075b953c6f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Experiment":"E4"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 33.2. Result ID: 69aa7e206dbb7075b953c6fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(b)","Ablation":"4.2","Experiment":"E12"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 32.8. Result ID: 69aa7e206dbb7075b953c6f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"8","Conn.":"(a)","Experiment":"E3"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 32.8. Result ID: 69aa7e206dbb7075b953c6fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(c)","Ablation":"4.2","Experiment":"E13"}. This record does not assert independent reproduction.

### LTU-7B

Accuracy: 32.5. Result ID: 69aa7e206dbb7075b953c6ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555aa.md>)

[Implementation](<https://github.com/YuanGongND/ltu>)

Recorded evaluation configuration: {"r":"8","Conn.":"Linear"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 32.5. Result ID: 69aa7e206dbb7075b953c6f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.1","Experiment":"E8"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 32.4. Result ID: 69aa7e206dbb7075b953c6fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(b)","Ablation":"4.2","Experiment":"E14"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 32.4. Result ID: 69aa7e206dbb7075b953c6ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(c)","Ablation":"4.2","Experiment":"E15"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 32. Result ID: 69aa7e206dbb7075b953c6fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(c)","Ablation":"4.2","Experiment":"E11"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 31.8. Result ID: 69aa7e206dbb7075b953c6f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.1","Experiment":"E9"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 31.7. Result ID: 69aa7e206dbb7075b953c6f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Experiment":"E5"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 31.6. Result ID: 69aa7e206dbb7075b953c6f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Experiment":"E6"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 31.6. Result ID: 69aa7e206dbb7075b953c6f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.1","Experiment":"E7"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 31.5. Result ID: 69aa7e206dbb7075b953c700.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.3","Experiment":"E16"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 30.9. Result ID: 69aa7e206dbb7075b953c6fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(b)","Ablation":"4.2","Experiment":"E10"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 30.7. Result ID: 69aa7e206dbb7075b953c701.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.3","Experiment":"E17"}. This record does not assert independent reproduction.

### SAM-780M

Accuracy: 29.4. Result ID: 69aa7e206dbb7075b953c6f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"8","Conn.":"(a)","Experiment":"E2"}. This record does not assert independent reproduction.

### SAM-130M

Accuracy: 29.2. Result ID: 69aa7e206dbb7075b953c6f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"8","Conn.":"(a)","Experiment":"E1"}. This record does not assert independent reproduction.

### SAM-2.7B

Accuracy: 27.7. Result ID: 69aa7e206dbb7075b953c702.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

Recorded evaluation configuration: {"r":"256","Conn.":"(a)","Ablation":"4.3","Experiment":"E18"}. This record does not assert independent reproduction.

### GAMA-7B

Accuracy: 21.5. Result ID: 69aa7e206dbb7075b953c6ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b721e209131cea8883d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a71e209131cea5db04.md>)

Recorded evaluation configuration: {"r":"8","Conn.":"QFormer"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
