# Speech Emotion Recognition on IEMOCAP Speaker-independent 5-fold cross-validation Source: [Speech Emotion Recognition on IEMOCAP Speaker-independent 5-fold cross-validation]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:21.706Z Evaluation of Speech Emotion Recognition performance on the speaker-independent 5-fold cross-validation setup of the IEMOCAP dataset, reporting Weighted Accuracy (WA). 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 | Speech Emotion Recognition | | Dataset (including any stated split) | IEMOCAP Speaker-independent 5-fold cross-validation | | Metric | WA | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [WA](): Higher is better; unit: PERCENT. - [UA](): Higher is better; unit: PERCENT. ## Recorded results | Method | WA | Result date | Report paper | | --- | --- | --- | --- | | Proposed Method | 78.47 | Not recorded | 69326756d6b0dd3342934562 | | Kang et al. \[8\] | 75.37 | Not recorded | 69326756d6b0dd3342934562 | | Wang et al. \[25\] | 75.2 | Not recorded | 69326756d6b0dd3342934562 | | Gao et al. \[23\] | 74.94 | Not recorded | 69326756d6b0dd3342934562 | | He et al. \[24\] | 74.5 | Not recorded | 69326756d6b0dd3342934562 | | HuBERT Large + Ours (TAP) | 74.2 | Not recorded | 68fa6dd31e209131cea3c35b | | HuBERT Large + Ours (SNP) | 73.9 | Not recorded | 68fa6dd31e209131cea3c35b | | He et al. \[22\] | 73.8 | Not recorded | 69326756d6b0dd3342934562 | | Wang et al. \[21\] | 73.37 | Not recorded | 69326756d6b0dd3342934562 | | Sun et al. \[20\] | 72.86 | Not recorded | 69326756d6b0dd3342934562 | | HuBERT Large | 71.9 | Not recorded | 68fa6dd31e209131cea3c35b | | AttPool | 71.7 | Not recorded | 68fa6dd31e209131cea3c35b | | Tang et al. \[19\] | 71.64 | Not recorded | 69326756d6b0dd3342934562 | | HuBERT Base + Ours (TAP) | 69.9 | Not recorded | 68fa6dd31e209131cea3c35b | | ACTC | 69 | Not recorded | 68fa6dd31e209131cea3c35b | | HuBERT Base + Ours (SNP) | 69 | Not recorded | 68fa6dd31e209131cea3c35b | | HuBERT Base | 68.9 | Not recorded | 68fa6dd31e209131cea3c35b | | wav2vec2-PT | 67.2 | Not recorded | 68fa6dd31e209131cea3c35b | | WISE | 66.5 | Not recorded | 68fa6dd31e209131cea3c35b | ### Proposed Method WA: 78.47. Result ID: 699a0f205698665ec492a8f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Kang et al. \[8\] WA: 75.37. Result ID: 699a0f205698665ec492a8ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Wang et al. \[25\] WA: 75.2. Result ID: 699a0f205698665ec492a8f1. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multi-modal"}. This record does not assert independent reproduction. ### Gao et al. \[23\] WA: 74.94. Result ID: 699a0f205698665ec492a8ee. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### He et al. \[24\] WA: 74.5. Result ID: 699a0f205698665ec492a8f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Multi-modal"}. This record does not assert independent reproduction. ### HuBERT Large + Ours (TAP) WA: 74.2. Result ID: 698fea1b3a6c314849fcc174. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"HuBERT Large","Strategy":"Train all parameters (TAP)"}. This record does not assert independent reproduction. ### HuBERT Large + Ours (SNP) WA: 73.9. Result ID: 698fea1b3a6c314849fcc173. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"HuBERT Large","Strategy":"Speaker normalization projector (SNP)"}. This record does not assert independent reproduction. ### He et al. \[22\] WA: 73.8. Result ID: 699a0f205698665ec492a8ed. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Wang et al. \[21\] WA: 73.37. Result ID: 699a0f205698665ec492a8ec. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Sun et al. \[20\] WA: 72.86. Result ID: 699a0f205698665ec492a8eb. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### HuBERT Large WA: 71.9. Result ID: 698fea1b3a6c314849fcc172. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"HuBERT Large"}. This record does not assert independent reproduction. ### AttPool WA: 71.7. Result ID: 698fea1b3a6c314849fcc16e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Tang et al. \[19\] WA: 71.64. Result ID: 699a0f205698665ec492a8ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### HuBERT Base + Ours (TAP) WA: 69.9. Result ID: 698fea1b3a6c314849fcc171. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"HuBERT Base","Strategy":"Train all parameters (TAP)"}. This record does not assert independent reproduction. ### ACTC WA: 69. Result ID: 698fea1b3a6c314849fcc16d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HuBERT Base + Ours (SNP) WA: 69. Result ID: 698fea1b3a6c314849fcc170. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"HuBERT Base","Strategy":"Speaker normalization projector (SNP)"}. This record does not assert independent reproduction. ### HuBERT Base WA: 68.9. Result ID: 698fea1b3a6c314849fcc16f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"HuBERT Base"}. This record does not assert independent reproduction. ### wav2vec2-PT WA: 67.2. Result ID: 698fea1b3a6c314849fcc16c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### WISE WA: 66.5. Result ID: 698fea1b3a6c314849fcc16b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.