# Urban Sound Classification on UrbanSound8K (test) Source: [Urban Sound Classification on UrbanSound8K (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:54.968Z Evaluation of urban sound classification performance using the test split of the UrbanSound8K dataset, 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 | Urban Sound Classification | | Dataset (including any stated split) | UrbanSound8K (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MUKA | 88.8 | Not recorded | 6993f68c9ebc499c97409eb3 | | Linear Probing | 85.64 | Not recorded | 6993f68c9ebc499c97409eb3 | | CLAP (Microsoft) | 82.74 | Not recorded | 692e72a5d6b0dd3342932398 | | WavCaps | 82.28 | Not recorded | 692e72a5d6b0dd3342932398 | | LAION-CLAP | 81.42 | Not recorded | 68fa737a1e209131cea5cc73 | | CLAP (LAION) | 80.91 | Not recorded | 692e72a5d6b0dd3342932398 | | PaLM | 80.77 | Not recorded | 6993f68c9ebc499c97409eb3 | | CACARA | 79.51 | Not recorded | 692e72a5d6b0dd3342932398 | | LanguageBind | 79.24 | Not recorded | 692e72a5d6b0dd3342932398 | | Treff-Adapter | 78.1 | Not recorded | 6993f68c9ebc499c97409eb3 | | CACARA | 77.83 | Not recorded | 692e72a5d6b0dd3342932398 | | CACARA | 77.4 | Not recorded | 692e72a5d6b0dd3342932398 | | CACARA | 77.04 | Not recorded | 692e72a5d6b0dd3342932398 | | CoCoOp | 76.52 | Not recorded | 6993f68c9ebc499c97409eb3 | | CoOp | 75.48 | Not recorded | 6993f68c9ebc499c97409eb3 | | CACARA | 75.4 | Not recorded | 692e72a5d6b0dd3342932398 | | Pengi | 75.29 | Not recorded | 68fa737a1e209131cea5cc73 | | CACARA | 74.99 | Not recorded | 692e72a5d6b0dd3342932398 | | M2D-CLAP | 72.4 | Not recorded | 68fa737a1e209131cea5cc73 | | CACARA | 70.04 | Not recorded | 692e72a5d6b0dd3342932398 | | AudioCLIP | 68.78 | Not recorded | 68fa737a1e209131cea5cc73 | | VAST | 68 | Not recorded | 692e72a5d6b0dd3342932398 | | Zero-Shot | 53.49 | Not recorded | 6993f68c9ebc499c97409eb3 | | ImageBind | 48.2 | Not recorded | 692e72a5d6b0dd3342932398 | | WavCaps | 44 | Not recorded | 68fa737a1e209131cea5cc73 | | Wav2CLIP | 40.44 | Not recorded | 68fa737a1e209131cea5cc73 | | CLAP2023 | 30 | Not recorded | 68fa737a1e209131cea5cc73 | | Proto-LC | 23.08 | Not recorded | 68fa737a1e209131cea5cc73 | ### MUKA Accuracy: 88.8. Result ID: 699a8ee15698665ec4195c52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Approach":"Training-free","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### Linear Probing Accuracy: 85.64. Result ID: 699a8ee15698665ec4195c4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Approach":"Training-based","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### CLAP (Microsoft) Accuracy: 82.74. Result ID: 6996d4975698665ec420ee5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"BM"}. This record does not assert independent reproduction. ### WavCaps Accuracy: 82.28. Result ID: 6996d4975698665ec420ee5c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"BM"}. This record does not assert independent reproduction. ### LAION-CLAP Accuracy: 81.42. Result ID: 6992e3853a6c314849122e84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. ### CLAP (LAION) Accuracy: 80.91. Result ID: 6996d4975698665ec420ee5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"BM"}. This record does not assert independent reproduction. ### PaLM Accuracy: 80.77. Result ID: 699a8ee15698665ec4195c4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Approach":"Training-based","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### CACARA Accuracy: 79.51. Result ID: 6996d4975698665ec420ee62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"WC/AC/C","f":0.1}. This record does not assert independent reproduction. ### LanguageBind Accuracy: 79.24. Result ID: 6996d4975698665ec420ee5f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"MM"}. This record does not assert independent reproduction. ### Treff-Adapter Accuracy: 78.1. Result ID: 699a8ee15698665ec4195c51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Approach":"Training-free","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### CACARA Accuracy: 77.83. Result ID: 6996d4975698665ec420ee63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"WC/AC/C","f":0.2}. This record does not assert independent reproduction. ### CACARA Accuracy: 77.4. Result ID: 6996d4975698665ec420ee61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"WC/AC/C"}. This record does not assert independent reproduction. ### CACARA Accuracy: 77.04. Result ID: 6996d4975698665ec420ee60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"AA/WC/AC/C"}. This record does not assert independent reproduction. ### CoCoOp Accuracy: 76.52. Result ID: 699a8ee15698665ec4195c4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Approach":"Training-based","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### CoOp Accuracy: 75.48. Result ID: 699a8ee15698665ec4195c4c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Approach":"Training-based","Shots":16,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### CACARA Accuracy: 75.4. Result ID: 6996d4975698665ec420ee65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"ASC/AA/WC/AC/C","f":0.1}. This record does not assert independent reproduction. ### Pengi Accuracy: 75.29. Result ID: 6992e3853a6c314849122e87. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. ### CACARA Accuracy: 74.99. Result ID: 6996d4975698665ec420ee66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"ASC/AA/WC/AC/C","f":0.2}. This record does not assert independent reproduction. ### M2D-CLAP Accuracy: 72.4. Result ID: 6992e3853a6c314849122e88. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"masking\_ratio":"0.7","zero-shot":true}. This record does not assert independent reproduction. ### CACARA Accuracy: 70.04. Result ID: 6996d4975698665ec420ee64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Components":"ASC/AA/WC/AC/C"}. This record does not assert independent reproduction. ### AudioCLIP Accuracy: 68.78. Result ID: 6992e3853a6c314849122e81. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"zero-shot":false,"note":"Used test task data during training"}. This record does not assert independent reproduction. ### VAST Accuracy: 68. Result ID: 6996d4975698665ec420ee5e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"MM"}. This record does not assert independent reproduction. ### Zero-Shot Accuracy: 53.49. Result ID: 699a8ee15698665ec4195c50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Approach":"Training-free","Shots":0,"Backbone":"PENGI"}. This record does not assert independent reproduction. ### ImageBind Accuracy: 48.2. Result ID: 6996d4975698665ec420ee5d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"MM"}. This record does not assert independent reproduction. ### WavCaps Accuracy: 44. Result ID: 6992e3853a6c314849122e83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. ### Wav2CLIP Accuracy: 40.44. Result ID: 6992e3853a6c314849122e82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. ### CLAP2023 Accuracy: 30. Result ID: 6992e3853a6c314849122e86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. ### Proto-LC Accuracy: 23.08. Result ID: 6992e3853a6c314849122e85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.